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

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

Neuron 2181 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.3511. Min Act: -0.0000

Data Index: 141155 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.3416. Min Act: -0.0000

Data Index: 212850 (C4 (Web Text))

Max Activating Token Index: 453

Text #2

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.3471. Min Act: -0.0000

Data Index: 351806 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.3077. Min Act: -0.0000

Data Index: 615193 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.3006. Min Act: -0.0000

Data Index: 782160 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2873. Min Act: -0.0000

Data Index: 593051 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2771. Min Act: -0.0000

Data Index: 82372 (C4 (Web Text))

Max Activating Token Index: 998

Text #7

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2823. Min Act: -0.0000

Data Index: 718262 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2892. Min Act: -0.0000

Data Index: 688403 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2805. Min Act: -0.0000

Data Index: 97840 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2802. Min Act: -0.0000

Data Index: 797659 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2725. Min Act: -0.0000

Data Index: 268605 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2737. Min Act: -0.0000

Data Index: 519496 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2638. Min Act: -0.0000

Data Index: 262815 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2720. Min Act: -0.0000

Data Index: 543385 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2677. Min Act: -0.0000

Data Index: 745253 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2468. Min Act: -0.0000

Data Index: 815164 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2634. Min Act: -0.0000

Data Index: 1167970 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2760. Min Act: -0.0000

Data Index: 1201638 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2566. Min Act: -0.0000

Data Index: 226906 (C4 (Web Text))

Max Activating Token Index: 367