< Prev | Home | Model | Random | Next >

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

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

Neuron 92 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: 4.6108. Min Range: -4.6108

Max Act: 4.5795. Min Act: -0.1700

Data Index: 440535 (C4 (Web Text))

Max Activating Token Index: 812

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.6108. Min Range: -4.6108

Max Act: 4.6108. Min Act: -0.1700

Data Index: 1377582 (Python Code)

Max Activating Token Index: 981

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.6108. Min Range: -4.6108

Max Act: 4.5795. Min Act: -0.1700

Data Index: 274178 (C4 (Web Text))

Max Activating Token Index: 852

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.6108. Min Range: -4.6108

Max Act: 4.5795. Min Act: -0.1692

Data Index: 1433204 (Python Code)

Max Activating Token Index: 120

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.6108. Min Range: -4.6108

Max Act: 4.5483. Min Act: -0.1700

Data Index: 833370 (C4 (Web Text))

Max Activating Token Index: 92

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.6108. Min Range: -4.6108

Max Act: 4.5483. Min Act: -0.1700

Data Index: 1309416 (C4 (Web Text))

Max Activating Token Index: 158

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.6108. Min Range: -4.6108

Max Act: 4.4858. Min Act: -0.1700

Data Index: 948191 (C4 (Web Text))

Max Activating Token Index: 911

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.6108. Min Range: -4.6108

Max Act: 4.5170. Min Act: -0.1700

Data Index: 978501 (C4 (Web Text))

Max Activating Token Index: 625

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.6108. Min Range: -4.6108

Max Act: 4.4858. Min Act: -0.1700

Data Index: 1365811 (Python Code)

Max Activating Token Index: 65

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.6108. Min Range: -4.6108

Max Act: 4.5170. Min Act: -0.1700

Data Index: 754222 (C4 (Web Text))

Max Activating Token Index: 45

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.6108. Min Range: -4.6108

Max Act: 4.4545. Min Act: -0.1700

Data Index: 944553 (C4 (Web Text))

Max Activating Token Index: 813

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.6108. Min Range: -4.6108

Max Act: 4.4858. Min Act: -0.1700

Data Index: 552848 (C4 (Web Text))

Max Activating Token Index: 974

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.6108. Min Range: -4.6108

Max Act: 4.4858. Min Act: -0.1700

Data Index: 916128 (C4 (Web Text))

Max Activating Token Index: 212

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.6108. Min Range: -4.6108

Max Act: 4.4545. Min Act: -0.1700

Data Index: 468639 (C4 (Web Text))

Max Activating Token Index: 831

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.6108. Min Range: -4.6108

Max Act: 4.4545. Min Act: -0.1700

Data Index: 988926 (C4 (Web Text))

Max Activating Token Index: 543

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.6108. Min Range: -4.6108

Max Act: 4.4545. Min Act: -0.1700

Data Index: 124241 (C4 (Web Text))

Max Activating Token Index: 792

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.6108. Min Range: -4.6108

Max Act: 4.4858. Min Act: -0.1699

Data Index: 413704 (C4 (Web Text))

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.6108. Min Range: -4.6108

Max Act: 4.4545. Min Act: -0.1700

Data Index: 1035776 (C4 (Web Text))

Max Activating Token Index: 124

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.6108. Min Range: -4.6108

Max Act: 4.3920. Min Act: -0.1700

Data Index: 23886 (C4 (Web Text))

Max Activating Token Index: 269

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.6108. Min Range: -4.6108

Max Act: 4.3608. Min Act: -0.1700

Data Index: 263247 (C4 (Web Text))

Max Activating Token Index: 878

Click toggle to see full text

Truncated

Full Text #19