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

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

Neuron 614 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0397. Min Act: -0.0006

Data Index: 1359458 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0369. Min Act: -0.0006

Data Index: 795200 (C4 (Web Text))

Max Activating Token Index: 460

Text #2

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0324. Min Act: -0.0006

Data Index: 1292900 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0316. Min Act: -0.0006

Data Index: 326066 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0337. Min Act: -0.0006

Data Index: 711694 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0308. Min Act: -0.0005

Data Index: 1078829 (C4 (Web Text))

Max Activating Token Index: 440

Text #6

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0299. Min Act: -0.0006

Data Index: 1132922 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0295. Min Act: -0.0006

Data Index: 497232 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0293. Min Act: -0.0006

Data Index: 1082743 (C4 (Web Text))

Max Activating Token Index: 494

Text #9

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0276. Min Act: -0.0006

Data Index: 1091878 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0310. Min Act: -0.0006

Data Index: 65396 (C4 (Web Text))

Max Activating Token Index: 995

Text #11

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0295. Min Act: -0.0006

Data Index: 1086472 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0294. Min Act: -0.0006

Data Index: 832973 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0299. Min Act: -0.0006

Data Index: 1176566 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0293. Min Act: -0.0006

Data Index: 328 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0285. Min Act: -0.0006

Data Index: 120516 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0280. Min Act: -0.0006

Data Index: 942385 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0305. Min Act: -0.0006

Data Index: 426444 (C4 (Web Text))

Max Activating Token Index: 441

Text #18

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0285. Min Act: -0.0006

Data Index: 213829 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0285. Min Act: -0.0006

Data Index: 974191 (C4 (Web Text))

Max Activating Token Index: 459