< Prev | Home | Model | Random | Next >

Model: GELU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1651 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')



Text #0

Max Range: 6.2908. Min Range: -6.2908

Max Act: 6.2596. Min Act: -0.0707

Data Index: 469810 (C4 (Web Text))

Max Activating Token Index: 115

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 6.2908. Min Range: -6.2908

Max Act: 6.2596. Min Act: -0.0764

Data Index: 850401 (C4 (Web Text))

Max Activating Token Index: 130

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 6.2908. Min Range: -6.2908

Max Act: 6.2908. Min Act: -0.0899

Data Index: 473939 (C4 (Web Text))

Max Activating Token Index: 142

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 6.2908. Min Range: -6.2908

Max Act: 6.1971. Min Act: -0.0358

Data Index: 491859 (C4 (Web Text))

Max Activating Token Index: 693

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 6.2908. Min Range: -6.2908

Max Act: 6.1346. Min Act: -0.1688

Data Index: 1411215 (Python Code)

Max Activating Token Index: 370

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 6.2908. Min Range: -6.2908

Max Act: 6.1658. Min Act: -0.1133

Data Index: 502548 (C4 (Web Text))

Max Activating Token Index: 368

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 6.2908. Min Range: -6.2908

Max Act: 6.1658. Min Act: -0.0144

Data Index: 669524 (C4 (Web Text))

Max Activating Token Index: 108

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 6.2908. Min Range: -6.2908

Max Act: 6.1658. Min Act: -0.1513

Data Index: 348431 (C4 (Web Text))

Max Activating Token Index: 287

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 6.2908. Min Range: -6.2908

Max Act: 6.1346. Min Act: -0.0792

Data Index: 368575 (C4 (Web Text))

Max Activating Token Index: 405

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 6.2908. Min Range: -6.2908

Max Act: 6.1346. Min Act: -0.1045

Data Index: 672696 (C4 (Web Text))

Max Activating Token Index: 219

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 6.2908. Min Range: -6.2908

Max Act: 6.1346. Min Act: -0.0924

Data Index: 640808 (C4 (Web Text))

Max Activating Token Index: 356

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 6.2908. Min Range: -6.2908

Max Act: 6.1033. Min Act: -0.0144

Data Index: 1146447 (C4 (Web Text))

Max Activating Token Index: 45

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 6.2908. Min Range: -6.2908

Max Act: 6.1033. Min Act: -0.0324

Data Index: 1212097 (C4 (Web Text))

Max Activating Token Index: 284

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 6.2908. Min Range: -6.2908

Max Act: 6.1346. Min Act: -0.1090

Data Index: 1041273 (C4 (Web Text))

Max Activating Token Index: 525

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 6.2908. Min Range: -6.2908

Max Act: 6.1346. Min Act: -0.1682

Data Index: 119963 (C4 (Web Text))

Max Activating Token Index: 389

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 6.2908. Min Range: -6.2908

Max Act: 6.1033. Min Act: -0.0899

Data Index: 76249 (C4 (Web Text))

Max Activating Token Index: 237

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 6.2908. Min Range: -6.2908

Max Act: 6.1346. Min Act: -0.1458

Data Index: 972255 (C4 (Web Text))

Max Activating Token Index: 584

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 6.2908. Min Range: -6.2908

Max Act: 6.1346. Min Act: -0.1175

Data Index: 837003 (C4 (Web Text))

Max Activating Token Index: 327

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 6.2908. Min Range: -6.2908

Max Act: 6.1033. Min Act: -0.1699

Data Index: 1498172 (Python Code)

Max Activating Token Index: 707

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 6.2908. Min Range: -6.2908

Max Act: 5.9783. Min Act: -0.1696

Data Index: 1610706 (Python Code)

Max Activating Token Index: 615

Click toggle to see full text

Truncated

Full Text #19