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

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

Neuron 1766 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3978. Min Act: -0.0000

Data Index: 1136608 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.2988. Min Act: -0.0000

Data Index: 406216 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.2838. Min Act: -0.0000

Data Index: 749119 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.2854. Min Act: -0.0000

Data Index: 756558 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.2954. Min Act: -0.0000

Data Index: 272540 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.2717. Min Act: -0.0000

Data Index: 475659 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.2322. Min Act: -0.0000

Data Index: 1234477 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.2172. Min Act: -0.0000

Data Index: 385081 (C4 (Web Text))

Max Activating Token Index: 875

Text #8

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.2489. Min Act: -0.0000

Data Index: 794782 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.2385. Min Act: -0.0000

Data Index: 289724 (C4 (Web Text))

Max Activating Token Index: 589

Text #10

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.2459. Min Act: -0.0000

Data Index: 1311933 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.2349. Min Act: -0.0000

Data Index: 549644 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.2237. Min Act: -0.0000

Data Index: 1519028 (Python Code)

Max Activating Token Index: 504

Text #13

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.2313. Min Act: -0.0000

Data Index: 420972 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.2246. Min Act: -0.0000

Data Index: 211403 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.2364. Min Act: -0.0000

Data Index: 637228 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.2368. Min Act: -0.0000

Data Index: 1125595 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.2247. Min Act: -0.0000

Data Index: 607028 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.2386. Min Act: -0.0000

Data Index: 381080 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.1981. Min Act: -0.0000

Data Index: 20706 (C4 (Web Text))

Max Activating Token Index: 13