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

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

Neuron 1275 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: 4.4541. Min Range: -4.4541

Max Act: 4.4541. Min Act: -0.1700

Data Index: 865237 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 4.4541. Min Range: -4.4541

Max Act: 4.2978. Min Act: -0.1700

Data Index: 924040 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 4.4541. Min Range: -4.4541

Max Act: 4.2978. Min Act: -0.1700

Data Index: 844256 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 4.4541. Min Range: -4.4541

Max Act: 4.2040. Min Act: -0.1700

Data Index: 348043 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 4.4541. Min Range: -4.4541

Max Act: 4.1415. Min Act: -0.1700

Data Index: 351166 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 4.4541. Min Range: -4.4541

Max Act: 4.1728. Min Act: -0.1700

Data Index: 964730 (C4 (Web Text))

Max Activating Token Index: 674

Text #6

Max Range: 4.4541. Min Range: -4.4541

Max Act: 4.1728. Min Act: -0.1700

Data Index: 829770 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 4.4541. Min Range: -4.4541

Max Act: 4.1415. Min Act: -0.1700

Data Index: 1269607 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 4.4541. Min Range: -4.4541

Max Act: 4.1103. Min Act: -0.1700

Data Index: 1357577 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 4.4541. Min Range: -4.4541

Max Act: 4.1103. Min Act: -0.1700

Data Index: 427345 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 4.4541. Min Range: -4.4541

Max Act: 4.0790. Min Act: -0.1700

Data Index: 386936 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 4.4541. Min Range: -4.4541

Max Act: 4.1103. Min Act: -0.1700

Data Index: 738066 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 4.4541. Min Range: -4.4541

Max Act: 4.0477. Min Act: -0.1700

Data Index: 1325411 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 4.4541. Min Range: -4.4541

Max Act: 4.0790. Min Act: -0.1700

Data Index: 862878 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 4.4541. Min Range: -4.4541

Max Act: 4.0790. Min Act: -0.1700

Data Index: 1323883 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 4.4541. Min Range: -4.4541

Max Act: 4.1103. Min Act: -0.1700

Data Index: 1315089 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 4.4541. Min Range: -4.4541

Max Act: 4.1103. Min Act: -0.1700

Data Index: 38404 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 4.4541. Min Range: -4.4541

Max Act: 4.0790. Min Act: -0.1700

Data Index: 456272 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 4.4541. Min Range: -4.4541

Max Act: 4.0477. Min Act: -0.1700

Data Index: 1038086 (C4 (Web Text))

Max Activating Token Index: 848

Text #19

Max Range: 4.4541. Min Range: -4.4541

Max Act: 4.0165. Min Act: -0.1700

Data Index: 1243043 (C4 (Web Text))

Max Activating Token Index: 48