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

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

Neuron 4246 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0457. Min Act: -0.0002

Data Index: 1447593 (Python Code)

Max Activating Token Index: 186

Text #1

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0448. Min Act: -0.0002

Data Index: 1541049 (Python Code)

Max Activating Token Index: 463

Text #2

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0431. Min Act: -0.0002

Data Index: 1374163 (Python Code)

Max Activating Token Index: 179

Text #3

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0400. Min Act: -0.0002

Data Index: 1233409 (C4 (Web Text))

Max Activating Token Index: 328

Text #4

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0331. Min Act: -0.0002

Data Index: 1579399 (Python Code)

Max Activating Token Index: 611

Text #5

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0337. Min Act: -0.0002

Data Index: 216418 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0320. Min Act: -0.0002

Data Index: 491761 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0302. Min Act: -0.0002

Data Index: 1546231 (Python Code)

Max Activating Token Index: 324

Text #8

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0285. Min Act: -0.0002

Data Index: 522569 (C4 (Web Text))

Max Activating Token Index: 609

Text #9

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0280. Min Act: -0.0002

Data Index: 327969 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0276. Min Act: -0.0002

Data Index: 281813 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0276. Min Act: -0.0002

Data Index: 440921 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0267. Min Act: -0.0002

Data Index: 1424649 (Python Code)

Max Activating Token Index: 283

Text #13

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0260. Min Act: -0.0002

Data Index: 696769 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0263. Min Act: -0.0002

Data Index: 1361425 (Python Code)

Max Activating Token Index: 133

Text #15

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0265. Min Act: -0.0002

Data Index: 779210 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0255. Min Act: -0.0002

Data Index: 1373068 (Python Code)

Max Activating Token Index: 439

Text #17

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0256. Min Act: -0.0002

Data Index: 1496554 (Python Code)

Max Activating Token Index: 202

Text #18

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0238. Min Act: -0.0002

Data Index: 1068577 (C4 (Web Text))

Max Activating Token Index: 762

Text #19

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0230. Min Act: -0.0002

Data Index: 71720 (C4 (Web Text))

Max Activating Token Index: 21