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

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

Neuron 25 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: 0.0352. Min Range: -0.0352

Max Act: 0.0352. Min Act: -0.0002

Data Index: 1411045 (Python Code)

Max Activating Token Index: 409

Text #1

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0337. Min Act: -0.0002

Data Index: 1535339 (Python Code)

Max Activating Token Index: 574

Text #2

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0290. Min Act: -0.0002

Data Index: 1371774 (Python Code)

Max Activating Token Index: 302

Text #3

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0290. Min Act: -0.0002

Data Index: 1608808 (Python Code)

Max Activating Token Index: 360

Text #4

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0288. Min Act: -0.0002

Data Index: 476220 (C4 (Web Text))

Max Activating Token Index: 352

Text #5

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0286. Min Act: -0.0002

Data Index: 102486 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0279. Min Act: -0.0002

Data Index: 1571997 (Python Code)

Max Activating Token Index: 27

Text #7

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0266. Min Act: -0.0002

Data Index: 1393937 (Python Code)

Max Activating Token Index: 824

Text #8

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0268. Min Act: -0.0002

Data Index: 1530723 (Python Code)

Max Activating Token Index: 720

Text #9

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0268. Min Act: -0.0002

Data Index: 1500418 (Python Code)

Max Activating Token Index: 140

Text #10

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0269. Min Act: -0.0002

Data Index: 1434448 (Python Code)

Max Activating Token Index: 147

Text #11

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0262. Min Act: -0.0002

Data Index: 1441150 (Python Code)

Max Activating Token Index: 123

Text #12

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0253. Min Act: -0.0002

Data Index: 1533596 (Python Code)

Max Activating Token Index: 893

Text #13

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0263. Min Act: -0.0002

Data Index: 1538050 (Python Code)

Max Activating Token Index: 483

Text #14

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0248. Min Act: -0.0002

Data Index: 1254197 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0248. Min Act: -0.0002

Data Index: 402477 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0250. Min Act: -0.0002

Data Index: 1643830 (Python Code)

Max Activating Token Index: 934

Text #17

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0250. Min Act: -0.0002

Data Index: 1621240 (Python Code)

Max Activating Token Index: 288

Text #18

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0242. Min Act: -0.0002

Data Index: 394053 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0246. Min Act: -0.0002

Data Index: 1414717 (Python Code)

Max Activating Token Index: 997