Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 463 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.3394. Min Act: -0.0000

Data Index: 993124 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.3208. Min Act: -0.0000

Data Index: 798038 (C4 (Web Text))

Max Activating Token Index: 531

Text #2

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.3309. Min Act: 0.0001

Data Index: 431599 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.3299. Min Act: -0.0000

Data Index: 410703 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.2909. Min Act: -0.0000

Data Index: 1113984 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.2962. Min Act: 0.0000

Data Index: 16341 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.3040. Min Act: -0.0000

Data Index: 570912 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.2840. Min Act: -0.0000

Data Index: 18486 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.2941. Min Act: -0.0000

Data Index: 623709 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.2786. Min Act: 0.0000

Data Index: 632421 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.2869. Min Act: 0.0000

Data Index: 424155 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.2901. Min Act: -0.0001

Data Index: 1142534 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.2770. Min Act: -0.0000

Data Index: 124488 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.2629. Min Act: -0.0000

Data Index: 18060 (C4 (Web Text))

Max Activating Token Index: 977

Text #14

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.2903. Min Act: -0.0001

Data Index: 637991 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.2773. Min Act: -0.0000

Data Index: 390261 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.2672. Min Act: -0.0000

Data Index: 1023281 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.2733. Min Act: -0.0000

Data Index: 701962 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.2475. Min Act: -0.0000

Data Index: 1218455 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 0.3394. Min Range: -0.3394

Max Act: 0.2511. Min Act: -0.0001

Data Index: 352151 (C4 (Web Text))

Max Activating Token Index: 701