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

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

Neuron 58 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8407. Min Range: -3.8407

Max Act: 3.8407. Min Act: -0.1700

Data Index: 1089177 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 3.8407. Min Range: -3.8407

Max Act: 3.7782. Min Act: -0.1700

Data Index: 1137510 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 3.8407. Min Range: -3.8407

Max Act: 3.8094. Min Act: -0.1700

Data Index: 1112865 (C4 (Web Text))

Max Activating Token Index: 425

Text #3

Max Range: 3.8407. Min Range: -3.8407

Max Act: 3.7782. Min Act: -0.1700

Data Index: 622181 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 3.8407. Min Range: -3.8407

Max Act: 3.7782. Min Act: -0.1700

Data Index: 890033 (C4 (Web Text))

Max Activating Token Index: 228

Text #5

Max Range: 3.8407. Min Range: -3.8407

Max Act: 3.7469. Min Act: -0.1700

Data Index: 877443 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 3.8407. Min Range: -3.8407

Max Act: 3.8094. Min Act: -0.1700

Data Index: 450741 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 3.8407. Min Range: -3.8407

Max Act: 3.7782. Min Act: -0.1700

Data Index: 1152646 (C4 (Web Text))

Max Activating Token Index: 769

Text #8

Max Range: 3.8407. Min Range: -3.8407

Max Act: 3.7469. Min Act: -0.1700

Data Index: 871408 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 3.8407. Min Range: -3.8407

Max Act: 3.7469. Min Act: -0.1700

Data Index: 87490 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 3.8407. Min Range: -3.8407

Max Act: 3.7469. Min Act: -0.1700

Data Index: 1031124 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 3.8407. Min Range: -3.8407

Max Act: 3.7469. Min Act: -0.1700

Data Index: 133761 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 3.8407. Min Range: -3.8407

Max Act: 3.6843. Min Act: -0.1700

Data Index: 367050 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 3.8407. Min Range: -3.8407

Max Act: 3.6843. Min Act: -0.1700

Data Index: 558572 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 3.8407. Min Range: -3.8407

Max Act: 3.7156. Min Act: -0.1700

Data Index: 726232 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 3.8407. Min Range: -3.8407

Max Act: 3.6843. Min Act: -0.1700

Data Index: 425677 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 3.8407. Min Range: -3.8407

Max Act: 3.7156. Min Act: -0.1700

Data Index: 810298 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 3.8407. Min Range: -3.8407

Max Act: 3.7156. Min Act: -0.1700

Data Index: 253638 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 3.8407. Min Range: -3.8407

Max Act: 3.6843. Min Act: -0.1700

Data Index: 584537 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 3.8407. Min Range: -3.8407

Max Act: 3.7156. Min Act: -0.1700

Data Index: 945959 (C4 (Web Text))

Max Activating Token Index: 65