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

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

Neuron 2131 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3192. Min Range: -1.3192

Max Act: 1.3192. Min Act: -0.0000

Data Index: 987939 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 1.3192. Min Range: -1.3192

Max Act: 1.2695. Min Act: -0.0000

Data Index: 1288885 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 1.3192. Min Range: -1.3192

Max Act: 1.1771. Min Act: -0.0001

Data Index: 749991 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 1.3192. Min Range: -1.3192

Max Act: 1.1304. Min Act: -0.0001

Data Index: 1210399 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 1.3192. Min Range: -1.3192

Max Act: 1.1356. Min Act: -0.0001

Data Index: 115985 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 1.3192. Min Range: -1.3192

Max Act: 1.1691. Min Act: -0.0001

Data Index: 202400 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 1.3192. Min Range: -1.3192

Max Act: 1.1244. Min Act: -0.0001

Data Index: 1320193 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 1.3192. Min Range: -1.3192

Max Act: 1.1209. Min Act: -0.0001

Data Index: 839298 (C4 (Web Text))

Max Activating Token Index: 512

Text #8

Max Range: 1.3192. Min Range: -1.3192

Max Act: 1.1732. Min Act: -0.0001

Data Index: 943949 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 1.3192. Min Range: -1.3192

Max Act: 1.1382. Min Act: -0.0001

Data Index: 1356590 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 1.3192. Min Range: -1.3192

Max Act: 1.1986. Min Act: -0.0001

Data Index: 40970 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 1.3192. Min Range: -1.3192

Max Act: 1.1329. Min Act: -0.0001

Data Index: 1299911 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 1.3192. Min Range: -1.3192

Max Act: 1.1263. Min Act: -0.0001

Data Index: 799982 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 1.3192. Min Range: -1.3192

Max Act: 1.1322. Min Act: -0.0001

Data Index: 915189 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 1.3192. Min Range: -1.3192

Max Act: 1.1040. Min Act: -0.0001

Data Index: 661919 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 1.3192. Min Range: -1.3192

Max Act: 1.1979. Min Act: -0.0000

Data Index: 725588 (C4 (Web Text))

Max Activating Token Index: 360

Text #16

Max Range: 1.3192. Min Range: -1.3192

Max Act: 1.1006. Min Act: -0.0001

Data Index: 460414 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 1.3192. Min Range: -1.3192

Max Act: 1.1247. Min Act: -0.0000

Data Index: 1348840 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 1.3192. Min Range: -1.3192

Max Act: 1.0954. Min Act: -0.0001

Data Index: 1233308 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 1.3192. Min Range: -1.3192

Max Act: 1.0971. Min Act: -0.0001

Data Index: 236626 (C4 (Web Text))

Max Activating Token Index: 510