Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3804 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0468. Min Act: -0.0001

Data Index: 765268 (C4 (Web Text))

Max Activating Token Index: 578

Text #1

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0401. Min Act: -0.0001

Data Index: 178319 (C4 (Web Text))

Max Activating Token Index: 337

Text #2

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0365. Min Act: -0.0001

Data Index: 293557 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0320. Min Act: -0.0001

Data Index: 806847 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0360. Min Act: -0.0001

Data Index: 336936 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0329. Min Act: -0.0001

Data Index: 41147 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0308. Min Act: -0.0001

Data Index: 155137 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0333. Min Act: -0.0001

Data Index: 591533 (C4 (Web Text))

Max Activating Token Index: 674

Text #8

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0314. Min Act: -0.0001

Data Index: 744804 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0328. Min Act: -0.0001

Data Index: 945068 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0291. Min Act: -0.0001

Data Index: 85768 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0284. Min Act: -0.0001

Data Index: 214549 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0263. Min Act: -0.0001

Data Index: 1191106 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0294. Min Act: -0.0001

Data Index: 285426 (C4 (Web Text))

Max Activating Token Index: 412

Text #14

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0287. Min Act: -0.0001

Data Index: 219753 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0282. Min Act: -0.0001

Data Index: 233793 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0248. Min Act: -0.0001

Data Index: 405721 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0280. Min Act: -0.0001

Data Index: 1337229 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0293. Min Act: -0.0001

Data Index: 768878 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0286. Min Act: -0.0001

Data Index: 1207384 (C4 (Web Text))

Max Activating Token Index: 62