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

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

Neuron 1377 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.4199. Min Range: -3.4199

Max Act: 3.4199. Min Act: -0.1700

Data Index: 328037 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.4199. Min Range: -3.4199

Max Act: 3.3728. Min Act: -0.1700

Data Index: 845456 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 3.4199. Min Range: -3.4199

Max Act: 3.3728. Min Act: -0.1700

Data Index: 1280004 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 3.4199. Min Range: -3.4199

Max Act: 3.3414. Min Act: -0.1700

Data Index: 1518441 (Python Code)

Max Activating Token Index: 11

Text #4

Max Range: 3.4199. Min Range: -3.4199

Max Act: 3.3728. Min Act: -0.1700

Data Index: 1249497 (C4 (Web Text))

Max Activating Token Index: 495

Text #5

Max Range: 3.4199. Min Range: -3.4199

Max Act: 3.3571. Min Act: -0.1700

Data Index: 262933 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 3.4199. Min Range: -3.4199

Max Act: 3.3257. Min Act: -0.1700

Data Index: 967152 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 3.4199. Min Range: -3.4199

Max Act: 3.3414. Min Act: -0.1700

Data Index: 1176344 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 3.4199. Min Range: -3.4199

Max Act: 3.3257. Min Act: -0.1700

Data Index: 380148 (C4 (Web Text))

Max Activating Token Index: 731

Text #9

Max Range: 3.4199. Min Range: -3.4199

Max Act: 3.3414. Min Act: -0.1700

Data Index: 1265048 (C4 (Web Text))

Max Activating Token Index: 576

Text #10

Max Range: 3.4199. Min Range: -3.4199

Max Act: 3.3100. Min Act: -0.1700

Data Index: 1163503 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 3.4199. Min Range: -3.4199

Max Act: 3.2943. Min Act: -0.1700

Data Index: 107826 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 3.4199. Min Range: -3.4199

Max Act: 3.2943. Min Act: -0.1700

Data Index: 1137671 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 3.4199. Min Range: -3.4199

Max Act: 3.2786. Min Act: -0.1700

Data Index: 151790 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 3.4199. Min Range: -3.4199

Max Act: 3.2629. Min Act: -0.1700

Data Index: 346637 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 3.4199. Min Range: -3.4199

Max Act: 3.2629. Min Act: -0.1700

Data Index: 962628 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 3.4199. Min Range: -3.4199

Max Act: 3.2472. Min Act: -0.1700

Data Index: 412268 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 3.4199. Min Range: -3.4199

Max Act: 3.2629. Min Act: -0.1700

Data Index: 820125 (C4 (Web Text))

Max Activating Token Index: 928

Text #18

Max Range: 3.4199. Min Range: -3.4199

Max Act: 3.2314. Min Act: -0.1700

Data Index: 956910 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 3.4199. Min Range: -3.4199

Max Act: 3.2472. Min Act: -0.1700

Data Index: 951532 (C4 (Web Text))

Max Activating Token Index: 225