< Prev | Home | Model | Random | Next >

Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 849 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')



Text #0

Max Range: 6.6483. Min Range: -6.6483

Max Act: 6.6483. Min Act: -0.1700

Data Index: 1254661 (C4 (Web Text))

Max Activating Token Index: 802

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 6.6483. Min Range: -6.6483

Max Act: 6.5545. Min Act: -0.1700

Data Index: 1335061 (C4 (Web Text))

Max Activating Token Index: 607

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 6.6483. Min Range: -6.6483

Max Act: 6.4920. Min Act: -0.1700

Data Index: 1378874 (Python Code)

Max Activating Token Index: 601

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 6.6483. Min Range: -6.6483

Max Act: 6.5233. Min Act: -0.1700

Data Index: 1479402 (Python Code)

Max Activating Token Index: 426

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 6.6483. Min Range: -6.6483

Max Act: 6.4764. Min Act: -0.1700

Data Index: 791058 (C4 (Web Text))

Max Activating Token Index: 159

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 6.6483. Min Range: -6.6483

Max Act: 6.4139. Min Act: -0.1700

Data Index: 1377073 (Python Code)

Max Activating Token Index: 59

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 6.6483. Min Range: -6.6483

Max Act: 6.4295. Min Act: -0.1700

Data Index: 661306 (C4 (Web Text))

Max Activating Token Index: 1017

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 6.6483. Min Range: -6.6483

Max Act: 6.4920. Min Act: -0.1700

Data Index: 170979 (C4 (Web Text))

Max Activating Token Index: 202

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 6.6483. Min Range: -6.6483

Max Act: 6.3983. Min Act: -0.1673

Data Index: 5093 (C4 (Web Text))

Max Activating Token Index: 405

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 6.6483. Min Range: -6.6483

Max Act: 6.3983. Min Act: -0.1700

Data Index: 1197247 (C4 (Web Text))

Max Activating Token Index: 737

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 6.6483. Min Range: -6.6483

Max Act: 6.4139. Min Act: -0.1700

Data Index: 706755 (C4 (Web Text))

Max Activating Token Index: 391

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 6.6483. Min Range: -6.6483

Max Act: 6.3514. Min Act: -0.1700

Data Index: 158185 (C4 (Web Text))

Max Activating Token Index: 69

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 6.6483. Min Range: -6.6483

Max Act: 6.3358. Min Act: -0.1275

Data Index: 1212934 (C4 (Web Text))

Max Activating Token Index: 115

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 6.6483. Min Range: -6.6483

Max Act: 6.4139. Min Act: 0.2240

Data Index: 175253 (C4 (Web Text))

Max Activating Token Index: 571

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 6.6483. Min Range: -6.6483

Max Act: 6.3670. Min Act: -0.1700

Data Index: 862254 (C4 (Web Text))

Max Activating Token Index: 127

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 6.6483. Min Range: -6.6483

Max Act: 6.3514. Min Act: -0.1700

Data Index: 702901 (C4 (Web Text))

Max Activating Token Index: 719

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 6.6483. Min Range: -6.6483

Max Act: 6.3358. Min Act: -0.1700

Data Index: 780001 (C4 (Web Text))

Max Activating Token Index: 315

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 6.6483. Min Range: -6.6483

Max Act: 6.2889. Min Act: -0.1700

Data Index: 830340 (C4 (Web Text))

Max Activating Token Index: 957

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 6.6483. Min Range: -6.6483

Max Act: 6.3202. Min Act: -0.1700

Data Index: 206144 (C4 (Web Text))

Max Activating Token Index: 804

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 6.6483. Min Range: -6.6483

Max Act: 6.2889. Min Act: -0.1700

Data Index: 518474 (C4 (Web Text))

Max Activating Token Index: 113

Click toggle to see full text

Truncated

Full Text #19