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

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

Neuron 1984 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: 0.4217. Min Range: -0.4217

Max Act: 0.4217. Min Act: -0.0000

Data Index: 402438 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.3498. Min Act: -0.0000

Data Index: 1111710 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.2823. Min Act: -0.0000

Data Index: 363450 (C4 (Web Text))

Max Activating Token Index: 832

Text #3

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.2528. Min Act: -0.0000

Data Index: 1209058 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.2618. Min Act: -0.0000

Data Index: 534596 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.2498. Min Act: -0.0000

Data Index: 1118124 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.2517. Min Act: -0.0000

Data Index: 730058 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.2207. Min Act: -0.0000

Data Index: 1203046 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.2276. Min Act: -0.0000

Data Index: 950434 (C4 (Web Text))

Max Activating Token Index: 446

Text #9

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.2209. Min Act: -0.0000

Data Index: 62451 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.2307. Min Act: -0.0000

Data Index: 756576 (C4 (Web Text))

Max Activating Token Index: 475

Text #11

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.2361. Min Act: -0.0000

Data Index: 701234 (C4 (Web Text))

Max Activating Token Index: 498

Text #12

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.2218. Min Act: -0.0000

Data Index: 794445 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.2234. Min Act: -0.0000

Data Index: 30472 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.2189. Min Act: -0.0000

Data Index: 87583 (C4 (Web Text))

Max Activating Token Index: 550

Text #15

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.2197. Min Act: -0.0000

Data Index: 514839 (C4 (Web Text))

Max Activating Token Index: 536

Text #16

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.2413. Min Act: -0.0000

Data Index: 929584 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.2103. Min Act: -0.0000

Data Index: 1300199 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.2106. Min Act: -0.0000

Data Index: 1864 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.2156. Min Act: -0.0000

Data Index: 1046178 (C4 (Web Text))

Max Activating Token Index: 481