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

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

Neuron 688 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0467. Min Act: -0.0001

Data Index: 1041920 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0314. Min Act: -0.0001

Data Index: 1174420 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0329. Min Act: -0.0001

Data Index: 55227 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0331. Min Act: -0.0001

Data Index: 1037361 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0320. Min Act: -0.0001

Data Index: 1323906 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0318. Min Act: -0.0001

Data Index: 192390 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0295. Min Act: -0.0001

Data Index: 1200358 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0319. Min Act: -0.0001

Data Index: 261034 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0320. Min Act: -0.0001

Data Index: 925484 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0307. Min Act: -0.0001

Data Index: 478737 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0315. Min Act: -0.0001

Data Index: 48212 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0268. Min Act: -0.0001

Data Index: 394478 (C4 (Web Text))

Max Activating Token Index: 385

Text #12

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0288. Min Act: -0.0001

Data Index: 1083637 (C4 (Web Text))

Max Activating Token Index: 570

Text #13

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0240. Min Act: -0.0001

Data Index: 542891 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0265. Min Act: -0.0001

Data Index: 1348995 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0241. Min Act: -0.0001

Data Index: 71770 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0256. Min Act: -0.0001

Data Index: 105751 (C4 (Web Text))

Max Activating Token Index: 782

Text #17

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0240. Min Act: -0.0001

Data Index: 132616 (C4 (Web Text))

Max Activating Token Index: 259

Text #18

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0266. Min Act: -0.0001

Data Index: 1057135 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0271. Min Act: -0.0001

Data Index: 613447 (C4 (Web Text))

Max Activating Token Index: 890