Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2596 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0327. Min Act: -0.0004

Data Index: 376886 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0319. Min Act: -0.0004

Data Index: 1263094 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0309. Min Act: -0.0004

Data Index: 80440 (C4 (Web Text))

Max Activating Token Index: 574

Text #3

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0321. Min Act: -0.0004

Data Index: 161666 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0293. Min Act: -0.0004

Data Index: 395441 (C4 (Web Text))

Max Activating Token Index: 774

Text #5

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0253. Min Act: -0.0004

Data Index: 1438392 (Python Code)

Max Activating Token Index: 621

Text #6

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0291. Min Act: -0.0004

Data Index: 387794 (C4 (Web Text))

Max Activating Token Index: 953

Text #7

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0283. Min Act: -0.0004

Data Index: 125897 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0271. Min Act: -0.0004

Data Index: 187396 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0273. Min Act: -0.0004

Data Index: 176062 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0260. Min Act: -0.0004

Data Index: 138349 (C4 (Web Text))

Max Activating Token Index: 714

Text #11

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0245. Min Act: -0.0004

Data Index: 1390886 (Python Code)

Max Activating Token Index: 690

Text #12

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0244. Min Act: -0.0004

Data Index: 1572012 (Python Code)

Max Activating Token Index: 635

Text #13

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0263. Min Act: -0.0004

Data Index: 1081844 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0250. Min Act: -0.0004

Data Index: 1140003 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0265. Min Act: -0.0004

Data Index: 157379 (C4 (Web Text))

Max Activating Token Index: 1001

Text #16

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0275. Min Act: -0.0004

Data Index: 528312 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0250. Min Act: -0.0004

Data Index: 1405605 (Python Code)

Max Activating Token Index: 352

Text #18

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0261. Min Act: -0.0004

Data Index: 1575057 (Python Code)

Max Activating Token Index: 985

Text #19

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0243. Min Act: -0.0004

Data Index: 395300 (C4 (Web Text))

Max Activating Token Index: 598