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

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

Neuron 3616 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3254. Min Range: -0.3254

Max Act: 0.3254. Min Act: -0.0000

Data Index: 615306 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 0.3254. Min Range: -0.3254

Max Act: 0.2656. Min Act: -0.0000

Data Index: 1308779 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 0.3254. Min Range: -0.3254

Max Act: 0.2838. Min Act: -0.0000

Data Index: 565003 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 0.3254. Min Range: -0.3254

Max Act: 0.2596. Min Act: -0.0000

Data Index: 284149 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 0.3254. Min Range: -0.3254

Max Act: 0.2446. Min Act: -0.0000

Data Index: 62295 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 0.3254. Min Range: -0.3254

Max Act: 0.2425. Min Act: -0.0000

Data Index: 410362 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 0.3254. Min Range: -0.3254

Max Act: 0.2413. Min Act: -0.0000

Data Index: 60399 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 0.3254. Min Range: -0.3254

Max Act: 0.2447. Min Act: -0.0000

Data Index: 281945 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 0.3254. Min Range: -0.3254

Max Act: 0.2444. Min Act: -0.0000

Data Index: 1066285 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 0.3254. Min Range: -0.3254

Max Act: 0.2375. Min Act: -0.0000

Data Index: 496663 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 0.3254. Min Range: -0.3254

Max Act: 0.2372. Min Act: -0.0000

Data Index: 381378 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 0.3254. Min Range: -0.3254

Max Act: 0.2343. Min Act: -0.0000

Data Index: 945372 (C4 (Web Text))

Max Activating Token Index: 623

Text #12

Max Range: 0.3254. Min Range: -0.3254

Max Act: 0.2320. Min Act: -0.0000

Data Index: 655606 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 0.3254. Min Range: -0.3254

Max Act: 0.2141. Min Act: -0.0000

Data Index: 1262821 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 0.3254. Min Range: -0.3254

Max Act: 0.2366. Min Act: -0.0000

Data Index: 150853 (C4 (Web Text))

Max Activating Token Index: 1004

Text #15

Max Range: 0.3254. Min Range: -0.3254

Max Act: 0.2246. Min Act: -0.0000

Data Index: 954696 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 0.3254. Min Range: -0.3254

Max Act: 0.2213. Min Act: -0.0000

Data Index: 1052069 (C4 (Web Text))

Max Activating Token Index: 514

Text #17

Max Range: 0.3254. Min Range: -0.3254

Max Act: 0.2140. Min Act: -0.0000

Data Index: 201192 (C4 (Web Text))

Max Activating Token Index: 106

Text #18

Max Range: 0.3254. Min Range: -0.3254

Max Act: 0.2271. Min Act: -0.0000

Data Index: 1234460 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 0.3254. Min Range: -0.3254

Max Act: 0.2197. Min Act: -0.0000

Data Index: 1136424 (C4 (Web Text))

Max Activating Token Index: 484