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

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

Neuron 4256 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: 0.0440. Min Range: -0.0440

Max Act: 0.0440. Min Act: -0.0002

Data Index: 780566 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0349. Min Act: -0.0002

Data Index: 910734 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0335. Min Act: -0.0002

Data Index: 879916 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0348. Min Act: -0.0002

Data Index: 1308095 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0346. Min Act: -0.0002

Data Index: 617121 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0325. Min Act: -0.0002

Data Index: 631223 (C4 (Web Text))

Max Activating Token Index: 954

Text #6

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0307. Min Act: -0.0002

Data Index: 303320 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0312. Min Act: -0.0002

Data Index: 907168 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0316. Min Act: -0.0002

Data Index: 723300 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0310. Min Act: -0.0002

Data Index: 387164 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0313. Min Act: -0.0002

Data Index: 931835 (C4 (Web Text))

Max Activating Token Index: 666

Text #11

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0292. Min Act: -0.0002

Data Index: 139201 (C4 (Web Text))

Max Activating Token Index: 753

Text #12

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0292. Min Act: -0.0002

Data Index: 1056742 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0310. Min Act: -0.0002

Data Index: 844125 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0294. Min Act: -0.0002

Data Index: 140742 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0276. Min Act: -0.0002

Data Index: 387495 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0286. Min Act: -0.0002

Data Index: 1081209 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0279. Min Act: -0.0002

Data Index: 1126646 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0274. Min Act: -0.0002

Data Index: 1323562 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0257. Min Act: -0.0002

Data Index: 1209856 (C4 (Web Text))

Max Activating Token Index: 784