Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3128 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0414. Min Act: -0.0000

Data Index: 1271744 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0406. Min Act: -0.0000

Data Index: 1161790 (C4 (Web Text))

Max Activating Token Index: 334

Text #2

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0376. Min Act: -0.0001

Data Index: 1226387 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0349. Min Act: -0.0000

Data Index: 149325 (C4 (Web Text))

Max Activating Token Index: 959

Text #4

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0345. Min Act: -0.0001

Data Index: 1189311 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0345. Min Act: -0.0001

Data Index: 376250 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0316. Min Act: -0.0000

Data Index: 304925 (C4 (Web Text))

Max Activating Token Index: 959

Text #7

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0308. Min Act: -0.0000

Data Index: 708238 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0314. Min Act: -0.0000

Data Index: 605895 (C4 (Web Text))

Max Activating Token Index: 330

Text #9

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0297. Min Act: -0.0001

Data Index: 737417 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0309. Min Act: -0.0001

Data Index: 1084629 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0294. Min Act: -0.0001

Data Index: 1400841 (Python Code)

Max Activating Token Index: 840

Text #12

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0277. Min Act: -0.0001

Data Index: 1434675 (Python Code)

Max Activating Token Index: 105

Text #13

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0329. Min Act: -0.0000

Data Index: 57540 (C4 (Web Text))

Max Activating Token Index: 348

Text #14

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0293. Min Act: -0.0000

Data Index: 960516 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0291. Min Act: -0.0000

Data Index: 1194704 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0291. Min Act: -0.0001

Data Index: 857313 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0295. Min Act: -0.0000

Data Index: 532113 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0284. Min Act: -0.0000

Data Index: 961859 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0282. Min Act: -0.0000

Data Index: 394717 (C4 (Web Text))

Max Activating Token Index: 532