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

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

Neuron 913 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: 5.4033. Min Range: -5.4033

Max Act: 5.3408. Min Act: -0.1700

Data Index: 718272 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 5.4033. Min Range: -5.4033

Max Act: 5.3720. Min Act: -0.1699

Data Index: 790080 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 5.4033. Min Range: -5.4033

Max Act: 5.4033. Min Act: -0.1700

Data Index: 30570 (C4 (Web Text))

Max Activating Token Index: 979

Text #3

Max Range: 5.4033. Min Range: -5.4033

Max Act: 5.3408. Min Act: -0.1700

Data Index: 1152162 (C4 (Web Text))

Max Activating Token Index: 733

Text #4

Max Range: 5.4033. Min Range: -5.4033

Max Act: 5.3408. Min Act: -0.1699

Data Index: 822278 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 5.4033. Min Range: -5.4033

Max Act: 5.3251. Min Act: -0.1700

Data Index: 754266 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 5.4033. Min Range: -5.4033

Max Act: 5.2470. Min Act: -0.1700

Data Index: 1331327 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 5.4033. Min Range: -5.4033

Max Act: 5.1533. Min Act: -0.1700

Data Index: 1008278 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 5.4033. Min Range: -5.4033

Max Act: 5.1533. Min Act: -0.1700

Data Index: 838070 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 5.4033. Min Range: -5.4033

Max Act: 5.1533. Min Act: -0.1700

Data Index: 833415 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 5.4033. Min Range: -5.4033

Max Act: 5.1376. Min Act: -0.1700

Data Index: 794958 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 5.4033. Min Range: -5.4033

Max Act: 5.1533. Min Act: -0.1699

Data Index: 180051 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 5.4033. Min Range: -5.4033

Max Act: 5.1376. Min Act: -0.1700

Data Index: 768807 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 5.4033. Min Range: -5.4033

Max Act: 5.0908. Min Act: -0.1699

Data Index: 168866 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 5.4033. Min Range: -5.4033

Max Act: 5.0126. Min Act: -0.1700

Data Index: 982210 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 5.4033. Min Range: -5.4033

Max Act: 5.0126. Min Act: -0.1700

Data Index: 694606 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 5.4033. Min Range: -5.4033

Max Act: 4.9814. Min Act: -0.1700

Data Index: 530057 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 5.4033. Min Range: -5.4033

Max Act: 5.0283. Min Act: -0.1699

Data Index: 576080 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 5.4033. Min Range: -5.4033

Max Act: 5.0126. Min Act: -0.1700

Data Index: 779793 (C4 (Web Text))

Max Activating Token Index: 246

Text #19

Max Range: 5.4033. Min Range: -5.4033

Max Act: 4.9501. Min Act: -0.1700

Data Index: 1124297 (C4 (Web Text))

Max Activating Token Index: 195