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

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

Neuron 577 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0349. Min Act: -0.0003

Data Index: 13980 (C4 (Web Text))

Max Activating Token Index: 269

Text #1

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0321. Min Act: -0.0003

Data Index: 702648 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0334. Min Act: -0.0003

Data Index: 1137671 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0349. Min Act: -0.0003

Data Index: 615714 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0322. Min Act: -0.0003

Data Index: 947104 (C4 (Web Text))

Max Activating Token Index: 487

Text #5

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0332. Min Act: -0.0003

Data Index: 86519 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0322. Min Act: -0.0003

Data Index: 727140 (C4 (Web Text))

Max Activating Token Index: 749

Text #7

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0328. Min Act: -0.0003

Data Index: 948451 (C4 (Web Text))

Max Activating Token Index: 491

Text #8

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0322. Min Act: -0.0003

Data Index: 336398 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0321. Min Act: -0.0003

Data Index: 1275215 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0326. Min Act: -0.0003

Data Index: 1335039 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0351. Min Act: -0.0003

Data Index: 1090982 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0343. Min Act: -0.0003

Data Index: 578934 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0291. Min Act: -0.0003

Data Index: 504987 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0342. Min Act: -0.0003

Data Index: 1231360 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0314. Min Act: -0.0003

Data Index: 392905 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0345. Min Act: -0.0003

Data Index: 1036887 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0312. Min Act: -0.0003

Data Index: 566693 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0369. Min Act: -0.0003

Data Index: 985145 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0333. Min Act: -0.0003

Data Index: 1288355 (C4 (Web Text))

Max Activating Token Index: 756