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

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

Neuron 750 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: 0.1615. Min Range: -0.1615

Max Act: 0.1575. Min Act: -0.0002

Data Index: 537227 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1615. Min Act: -0.0002

Data Index: 323497 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1487. Min Act: -0.0002

Data Index: 807124 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1335. Min Act: -0.0002

Data Index: 277322 (C4 (Web Text))

Max Activating Token Index: 363

Text #4

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1392. Min Act: -0.0002

Data Index: 622223 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1296. Min Act: -0.0001

Data Index: 1074941 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1243. Min Act: -0.0002

Data Index: 159028 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1298. Min Act: -0.0002

Data Index: 202583 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1286. Min Act: -0.0002

Data Index: 961276 (C4 (Web Text))

Max Activating Token Index: 379

Text #9

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1263. Min Act: -0.0002

Data Index: 125979 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1243. Min Act: -0.0002

Data Index: 1050363 (C4 (Web Text))

Max Activating Token Index: 738

Text #11

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1260. Min Act: -0.0002

Data Index: 1102225 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1226. Min Act: -0.0002

Data Index: 322364 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1277. Min Act: -0.0002

Data Index: 147329 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1224. Min Act: -0.0002

Data Index: 440501 (C4 (Web Text))

Max Activating Token Index: 469

Text #15

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1153. Min Act: -0.0002

Data Index: 757166 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1224. Min Act: -0.0002

Data Index: 859394 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1190. Min Act: -0.0002

Data Index: 104948 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1147. Min Act: -0.0002

Data Index: 84983 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1159. Min Act: -0.0002

Data Index: 782043 (C4 (Web Text))

Max Activating Token Index: 837