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

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

Neuron 3966 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: 0.7231. Min Range: -0.7231

Max Act: 0.7231. Min Act: -0.0000

Data Index: 1250611 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 0.7231. Min Range: -0.7231

Max Act: 0.5649. Min Act: -0.0000

Data Index: 49678 (C4 (Web Text))

Max Activating Token Index: 593

Text #2

Max Range: 0.7231. Min Range: -0.7231

Max Act: 0.5377. Min Act: -0.0000

Data Index: 207899 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 0.7231. Min Range: -0.7231

Max Act: 0.5521. Min Act: -0.0000

Data Index: 93124 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 0.7231. Min Range: -0.7231

Max Act: 0.5315. Min Act: -0.0000

Data Index: 258370 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 0.7231. Min Range: -0.7231

Max Act: 0.5013. Min Act: -0.0000

Data Index: 500995 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 0.7231. Min Range: -0.7231

Max Act: 0.4954. Min Act: -0.0000

Data Index: 1212335 (C4 (Web Text))

Max Activating Token Index: 298

Text #7

Max Range: 0.7231. Min Range: -0.7231

Max Act: 0.4844. Min Act: -0.0000

Data Index: 641160 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 0.7231. Min Range: -0.7231

Max Act: 0.5158. Min Act: -0.0000

Data Index: 1123172 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 0.7231. Min Range: -0.7231

Max Act: 0.4793. Min Act: -0.0000

Data Index: 389043 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 0.7231. Min Range: -0.7231

Max Act: 0.4415. Min Act: -0.0000

Data Index: 1388281 (Python Code)

Max Activating Token Index: 80

Text #11

Max Range: 0.7231. Min Range: -0.7231

Max Act: 0.4225. Min Act: -0.0000

Data Index: 199961 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 0.7231. Min Range: -0.7231

Max Act: 0.4542. Min Act: -0.0000

Data Index: 180059 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 0.7231. Min Range: -0.7231

Max Act: 0.4322. Min Act: -0.0000

Data Index: 39510 (C4 (Web Text))

Max Activating Token Index: 403

Text #14

Max Range: 0.7231. Min Range: -0.7231

Max Act: 0.4274. Min Act: -0.0000

Data Index: 1160273 (C4 (Web Text))

Max Activating Token Index: 330

Text #15

Max Range: 0.7231. Min Range: -0.7231

Max Act: 0.4104. Min Act: -0.0000

Data Index: 488083 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 0.7231. Min Range: -0.7231

Max Act: 0.4189. Min Act: -0.0000

Data Index: 106194 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 0.7231. Min Range: -0.7231

Max Act: 0.4072. Min Act: -0.0000

Data Index: 608271 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 0.7231. Min Range: -0.7231

Max Act: 0.4357. Min Act: -0.0000

Data Index: 517803 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 0.7231. Min Range: -0.7231

Max Act: 0.4184. Min Act: -0.0000

Data Index: 93991 (C4 (Web Text))

Max Activating Token Index: 420