Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 469 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0338. Min Act: -0.0002

Data Index: 766194 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0268. Min Act: -0.0002

Data Index: 358684 (C4 (Web Text))

Max Activating Token Index: 379

Text #2

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0260. Min Act: -0.0002

Data Index: 1082846 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0249. Min Act: -0.0001

Data Index: 1648331 (Python Code)

Max Activating Token Index: 885

Text #4

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0243. Min Act: -0.0001

Data Index: 903446 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0241. Min Act: -0.0002

Data Index: 1323408 (C4 (Web Text))

Max Activating Token Index: 507

Text #6

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0235. Min Act: -0.0002

Data Index: 786065 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0239. Min Act: -0.0002

Data Index: 23700 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0234. Min Act: -0.0002

Data Index: 482374 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0243. Min Act: -0.0002

Data Index: 117979 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0233. Min Act: -0.0002

Data Index: 1307752 (C4 (Web Text))

Max Activating Token Index: 698

Text #11

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0235. Min Act: -0.0002

Data Index: 959240 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0234. Min Act: -0.0002

Data Index: 1061979 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0231. Min Act: -0.0002

Data Index: 1627631 (Python Code)

Max Activating Token Index: 492

Text #14

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0230. Min Act: -0.0002

Data Index: 1457236 (Python Code)

Max Activating Token Index: 110

Text #15

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0232. Min Act: -0.0002

Data Index: 243538 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0233. Min Act: -0.0002

Data Index: 333037 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0235. Min Act: -0.0002

Data Index: 1625774 (Python Code)

Max Activating Token Index: 834

Text #18

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0226. Min Act: -0.0002

Data Index: 1343649 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0226. Min Act: -0.0001

Data Index: 1032250 (C4 (Web Text))

Max Activating Token Index: 591