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

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

Neuron 2173 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.3342. Min Act: -0.0000

Data Index: 571210 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2712. Min Act: -0.0000

Data Index: 82127 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2766. Min Act: -0.0000

Data Index: 907329 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2669. Min Act: -0.0000

Data Index: 1165919 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2543. Min Act: -0.0000

Data Index: 1196130 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2644. Min Act: -0.0000

Data Index: 847395 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2436. Min Act: -0.0000

Data Index: 1051634 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2385. Min Act: -0.0000

Data Index: 264644 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2635. Min Act: -0.0000

Data Index: 1057652 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2386. Min Act: -0.0000

Data Index: 1207685 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2350. Min Act: -0.0000

Data Index: 1034902 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2413. Min Act: -0.0000

Data Index: 908923 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2409. Min Act: -0.0000

Data Index: 386654 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2216. Min Act: -0.0000

Data Index: 1324062 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2434. Min Act: -0.0000

Data Index: 496060 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2476. Min Act: -0.0000

Data Index: 573316 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2394. Min Act: -0.0000

Data Index: 89915 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2345. Min Act: -0.0000

Data Index: 328363 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2323. Min Act: -0.0000

Data Index: 857759 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2115. Min Act: -0.0000

Data Index: 1206923 (C4 (Web Text))

Max Activating Token Index: 579