Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 679 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.9230. Min Act: -0.0000

Data Index: 299866 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.8226. Min Act: -0.0000

Data Index: 572420 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.8002. Min Act: -0.0000

Data Index: 138855 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.8172. Min Act: -0.0000

Data Index: 663959 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7795. Min Act: -0.0000

Data Index: 1032285 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7099. Min Act: -0.0000

Data Index: 972328 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.6759. Min Act: -0.0000

Data Index: 1047614 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.6685. Min Act: -0.0000

Data Index: 468139 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.6513. Min Act: -0.0000

Data Index: 403305 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.6148. Min Act: -0.0000

Data Index: 794961 (C4 (Web Text))

Max Activating Token Index: 226

Text #10

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.5894. Min Act: -0.0000

Data Index: 1334954 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.5950. Min Act: -0.0000

Data Index: 665752 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.5766. Min Act: -0.0000

Data Index: 1135324 (C4 (Web Text))

Max Activating Token Index: 353

Text #13

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.5915. Min Act: -0.0000

Data Index: 126290 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.5732. Min Act: -0.0000

Data Index: 1147689 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.5386. Min Act: -0.0000

Data Index: 252461 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.5426. Min Act: -0.0000

Data Index: 948543 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.5519. Min Act: -0.0000

Data Index: 639237 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.5345. Min Act: -0.0000

Data Index: 735975 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.5138. Min Act: -0.0000

Data Index: 1286589 (C4 (Web Text))

Max Activating Token Index: 330