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

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

Neuron 4652 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2908. Min Act: -0.0000

Data Index: 493540 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2900. Min Act: -0.0000

Data Index: 137666 (C4 (Web Text))

Max Activating Token Index: 694

Text #2

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2440. Min Act: -0.0000

Data Index: 1091127 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2591. Min Act: -0.0000

Data Index: 644869 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2374. Min Act: -0.0000

Data Index: 606461 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2516. Min Act: -0.0000

Data Index: 29649 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2500. Min Act: -0.0000

Data Index: 1351615 (C4 (Web Text))

Max Activating Token Index: 788

Text #7

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2416. Min Act: -0.0000

Data Index: 531472 (C4 (Web Text))

Max Activating Token Index: 471

Text #8

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2460. Min Act: -0.0000

Data Index: 1295469 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2326. Min Act: -0.0000

Data Index: 592894 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2353. Min Act: -0.0000

Data Index: 206217 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2496. Min Act: -0.0000

Data Index: 205297 (C4 (Web Text))

Max Activating Token Index: 897

Text #12

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2223. Min Act: -0.0000

Data Index: 285147 (C4 (Web Text))

Max Activating Token Index: 339

Text #13

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2164. Min Act: -0.0000

Data Index: 220893 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2207. Min Act: -0.0000

Data Index: 853245 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2370. Min Act: -0.0001

Data Index: 40003 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2195. Min Act: -0.0000

Data Index: 1200688 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2161. Min Act: -0.0000

Data Index: 338315 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2409. Min Act: -0.0000

Data Index: 230052 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 0.2908. Min Range: -0.2908

Max Act: 0.2017. Min Act: -0.0000

Data Index: 1100690 (C4 (Web Text))

Max Activating Token Index: 888