Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5696 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.5524. Min Range: -5.5524

Max Act: 5.5524. Min Act: -0.0000

Data Index: 1043749 (C4 (Web Text))

Max Activating Token Index: 187

Text #1

Max Range: 5.5524. Min Range: -5.5524

Max Act: 4.7790. Min Act: -0.0000

Data Index: 1206915 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 5.5524. Min Range: -5.5524

Max Act: 4.7359. Min Act: -0.0000

Data Index: 309253 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 5.5524. Min Range: -5.5524

Max Act: 4.7240. Min Act: -0.0000

Data Index: 459013 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 5.5524. Min Range: -5.5524

Max Act: 4.8469. Min Act: -0.0000

Data Index: 1334061 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 5.5524. Min Range: -5.5524

Max Act: 4.4479. Min Act: -0.0000

Data Index: 1029343 (C4 (Web Text))

Max Activating Token Index: 734

Text #6

Max Range: 5.5524. Min Range: -5.5524

Max Act: 4.4752. Min Act: -0.0000

Data Index: 733976 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 5.5524. Min Range: -5.5524

Max Act: 4.5396. Min Act: -0.0000

Data Index: 1320933 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 5.5524. Min Range: -5.5524

Max Act: 4.2314. Min Act: -0.0000

Data Index: 122765 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 5.5524. Min Range: -5.5524

Max Act: 4.5743. Min Act: -0.0000

Data Index: 483241 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 5.5524. Min Range: -5.5524

Max Act: 4.3132. Min Act: -0.0000

Data Index: 1225084 (C4 (Web Text))

Max Activating Token Index: 888

Text #11

Max Range: 5.5524. Min Range: -5.5524

Max Act: 4.3178. Min Act: -0.0000

Data Index: 22415 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 5.5524. Min Range: -5.5524

Max Act: 4.1043. Min Act: -0.0000

Data Index: 540711 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 5.5524. Min Range: -5.5524

Max Act: 4.2415. Min Act: -0.0000

Data Index: 906346 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 5.5524. Min Range: -5.5524

Max Act: 4.0441. Min Act: -0.0000

Data Index: 1078597 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 5.5524. Min Range: -5.5524

Max Act: 4.0208. Min Act: -0.0000

Data Index: 40539 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 5.5524. Min Range: -5.5524

Max Act: 3.9663. Min Act: -0.0000

Data Index: 1015483 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 5.5524. Min Range: -5.5524

Max Act: 4.0150. Min Act: -0.0000

Data Index: 477890 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 5.5524. Min Range: -5.5524

Max Act: 4.1220. Min Act: -0.0000

Data Index: 323170 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 5.5524. Min Range: -5.5524

Max Act: 3.9972. Min Act: -0.0000

Data Index: 247100 (C4 (Web Text))

Max Activating Token Index: 104