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

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

Neuron 6000 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0413. Min Act: -0.0002

Data Index: 165548 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0378. Min Act: -0.0002

Data Index: 848172 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0384. Min Act: -0.0002

Data Index: 948525 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0371. Min Act: -0.0002

Data Index: 982160 (C4 (Web Text))

Max Activating Token Index: 436

Text #4

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0349. Min Act: -0.0002

Data Index: 981911 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0338. Min Act: -0.0002

Data Index: 63188 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0343. Min Act: -0.0002

Data Index: 1071352 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0338. Min Act: -0.0002

Data Index: 1217228 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0328. Min Act: -0.0002

Data Index: 316631 (C4 (Web Text))

Max Activating Token Index: 330

Text #9

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0338. Min Act: -0.0002

Data Index: 27828 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0336. Min Act: -0.0002

Data Index: 240958 (C4 (Web Text))

Max Activating Token Index: 649

Text #11

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0331. Min Act: -0.0002

Data Index: 1233243 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0334. Min Act: -0.0002

Data Index: 289776 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0328. Min Act: -0.0002

Data Index: 305897 (C4 (Web Text))

Max Activating Token Index: 336

Text #14

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0324. Min Act: -0.0002

Data Index: 821952 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0318. Min Act: -0.0002

Data Index: 423635 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0321. Min Act: -0.0002

Data Index: 211660 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0310. Min Act: -0.0002

Data Index: 750857 (C4 (Web Text))

Max Activating Token Index: 572

Text #18

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0314. Min Act: -0.0002

Data Index: 534521 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0308. Min Act: -0.0002

Data Index: 936147 (C4 (Web Text))

Max Activating Token Index: 724