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

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

Neuron 2724 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4969. Min Range: -2.4969

Max Act: 2.4692. Min Act: -0.0000

Data Index: 381285 (C4 (Web Text))

Max Activating Token Index: 493

Text #1

Max Range: 2.4969. Min Range: -2.4969

Max Act: 2.4969. Min Act: -0.0000

Data Index: 189824 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 2.4969. Min Range: -2.4969

Max Act: 2.2987. Min Act: -0.0000

Data Index: 439657 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 2.4969. Min Range: -2.4969

Max Act: 2.2538. Min Act: -0.0000

Data Index: 183304 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 2.4969. Min Range: -2.4969

Max Act: 2.3466. Min Act: -0.0000

Data Index: 905941 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 2.4969. Min Range: -2.4969

Max Act: 2.3304. Min Act: -0.0000

Data Index: 728468 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 2.4969. Min Range: -2.4969

Max Act: 2.1684. Min Act: -0.0000

Data Index: 1107266 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 2.4969. Min Range: -2.4969

Max Act: 2.1850. Min Act: -0.0000

Data Index: 1197067 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 2.4969. Min Range: -2.4969

Max Act: 2.2776. Min Act: -0.0000

Data Index: 289857 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 2.4969. Min Range: -2.4969

Max Act: 2.2777. Min Act: -0.0000

Data Index: 386488 (C4 (Web Text))

Max Activating Token Index: 212

Text #10

Max Range: 2.4969. Min Range: -2.4969

Max Act: 2.2723. Min Act: -0.0000

Data Index: 336463 (C4 (Web Text))

Max Activating Token Index: 496

Text #11

Max Range: 2.4969. Min Range: -2.4969

Max Act: 2.2582. Min Act: -0.0000

Data Index: 63651 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 2.4969. Min Range: -2.4969

Max Act: 2.3793. Min Act: -0.0000

Data Index: 210362 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 2.4969. Min Range: -2.4969

Max Act: 2.2516. Min Act: -0.0000

Data Index: 594163 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 2.4969. Min Range: -2.4969

Max Act: 2.2511. Min Act: -0.0000

Data Index: 141616 (C4 (Web Text))

Max Activating Token Index: 951

Text #15

Max Range: 2.4969. Min Range: -2.4969

Max Act: 2.2438. Min Act: -0.0000

Data Index: 872253 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 2.4969. Min Range: -2.4969

Max Act: 2.2310. Min Act: -0.0000

Data Index: 644398 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 2.4969. Min Range: -2.4969

Max Act: 2.2350. Min Act: -0.0000

Data Index: 535475 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 2.4969. Min Range: -2.4969

Max Act: 2.2156. Min Act: -0.0000

Data Index: 577808 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 2.4969. Min Range: -2.4969

Max Act: 2.1912. Min Act: -0.0000

Data Index: 342779 (C4 (Web Text))

Max Activating Token Index: 318