Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 15 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.5549. Min Range: -5.5549

Max Act: 5.5549. Min Act: -0.1700

Data Index: 1245534 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 5.5549. Min Range: -5.5549

Max Act: 5.3049. Min Act: -0.1700

Data Index: 890880 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 5.5549. Min Range: -5.5549

Max Act: 5.2737. Min Act: -0.1700

Data Index: 553030 (C4 (Web Text))

Max Activating Token Index: 658

Text #3

Max Range: 5.5549. Min Range: -5.5549

Max Act: 5.2112. Min Act: -0.1700

Data Index: 812062 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 5.5549. Min Range: -5.5549

Max Act: 5.2737. Min Act: -0.1700

Data Index: 1210855 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 5.5549. Min Range: -5.5549

Max Act: 5.2112. Min Act: -0.1700

Data Index: 1072052 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 5.5549. Min Range: -5.5549

Max Act: 5.3049. Min Act: -0.1700

Data Index: 380279 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 5.5549. Min Range: -5.5549

Max Act: 5.2424. Min Act: -0.1700

Data Index: 77201 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 5.5549. Min Range: -5.5549

Max Act: 5.1799. Min Act: -0.1700

Data Index: 174397 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 5.5549. Min Range: -5.5549

Max Act: 5.1799. Min Act: -0.1700

Data Index: 1350409 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 5.5549. Min Range: -5.5549

Max Act: 5.2424. Min Act: -0.1700

Data Index: 453421 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 5.5549. Min Range: -5.5549

Max Act: 5.2112. Min Act: -0.1700

Data Index: 629506 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 5.5549. Min Range: -5.5549

Max Act: 5.1799. Min Act: -0.1700

Data Index: 1308449 (C4 (Web Text))

Max Activating Token Index: 335

Text #13

Max Range: 5.5549. Min Range: -5.5549

Max Act: 5.2737. Min Act: -0.1700

Data Index: 440462 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 5.5549. Min Range: -5.5549

Max Act: 5.2424. Min Act: -0.1700

Data Index: 632987 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 5.5549. Min Range: -5.5549

Max Act: 5.2424. Min Act: -0.1700

Data Index: 1229918 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 5.5549. Min Range: -5.5549

Max Act: 5.2112. Min Act: -0.1700

Data Index: 1291163 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 5.5549. Min Range: -5.5549

Max Act: 5.2112. Min Act: -0.1700

Data Index: 177228 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 5.5549. Min Range: -5.5549

Max Act: 5.2112. Min Act: -0.1700

Data Index: 363356 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 5.5549. Min Range: -5.5549

Max Act: 5.2424. Min Act: -0.1700

Data Index: 904910 (C4 (Web Text))

Max Activating Token Index: 961