Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2560 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0472. Min Act: -0.0002

Data Index: 613098 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0448. Min Act: -0.0001

Data Index: 761390 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0449. Min Act: -0.0002

Data Index: 485083 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0432. Min Act: -0.0002

Data Index: 124369 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0404. Min Act: -0.0002

Data Index: 703414 (C4 (Web Text))

Max Activating Token Index: 169

Text #5

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0400. Min Act: -0.0002

Data Index: 1228314 (C4 (Web Text))

Max Activating Token Index: 126

Text #6

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0395. Min Act: -0.0002

Data Index: 121493 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0380. Min Act: -0.0002

Data Index: 600968 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0386. Min Act: -0.0002

Data Index: 64669 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0361. Min Act: -0.0002

Data Index: 1225177 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0353. Min Act: -0.0002

Data Index: 62022 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0356. Min Act: -0.0002

Data Index: 243780 (C4 (Web Text))

Max Activating Token Index: 733

Text #12

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0329. Min Act: -0.0002

Data Index: 48752 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0335. Min Act: -0.0002

Data Index: 1135496 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0328. Min Act: -0.0002

Data Index: 1324680 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0320. Min Act: -0.0002

Data Index: 1260266 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0333. Min Act: -0.0002

Data Index: 559724 (C4 (Web Text))

Max Activating Token Index: 477

Text #17

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0329. Min Act: -0.0002

Data Index: 79622 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0318. Min Act: -0.0002

Data Index: 1069107 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0318. Min Act: -0.0003

Data Index: 1049440 (C4 (Web Text))

Max Activating Token Index: 271