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

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

Neuron 2952 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.5207. Min Act: -0.0001

Data Index: 457426 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.4178. Min Act: -0.0000

Data Index: 96113 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3757. Min Act: -0.0001

Data Index: 268457 (C4 (Web Text))

Max Activating Token Index: 812

Text #3

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3750. Min Act: -0.0000

Data Index: 417599 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3121. Min Act: -0.0000

Data Index: 162394 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3198. Min Act: -0.0001

Data Index: 594610 (C4 (Web Text))

Max Activating Token Index: 895

Text #6

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3232. Min Act: -0.0001

Data Index: 40744 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.2989. Min Act: -0.0000

Data Index: 1158710 (C4 (Web Text))

Max Activating Token Index: 569

Text #8

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.2804. Min Act: -0.0001

Data Index: 8977 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.2697. Min Act: -0.0000

Data Index: 567634 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.2512. Min Act: -0.0000

Data Index: 1322529 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.2854. Min Act: -0.0000

Data Index: 929084 (C4 (Web Text))

Max Activating Token Index: 431

Text #12

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.2816. Min Act: -0.0000

Data Index: 409935 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.2800. Min Act: -0.0001

Data Index: 5048 (C4 (Web Text))

Max Activating Token Index: 544

Text #14

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.2703. Min Act: -0.0001

Data Index: 387055 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.2548. Min Act: -0.0000

Data Index: 277632 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.2725. Min Act: -0.0001

Data Index: 1291797 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.2689. Min Act: -0.0001

Data Index: 753457 (C4 (Web Text))

Max Activating Token Index: 497

Text #18

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.2185. Min Act: -0.0000

Data Index: 1221767 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.2711. Min Act: -0.0000

Data Index: 478176 (C4 (Web Text))

Max Activating Token Index: 528