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

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

Neuron 932 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: 0.3423. Min Range: -0.3423

Max Act: 0.3423. Min Act: -0.0000

Data Index: 424504 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.3259. Min Act: -0.0000

Data Index: 1264217 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.3298. Min Act: -0.0000

Data Index: 696045 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.3362. Min Act: -0.0000

Data Index: 1309902 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.3296. Min Act: -0.0000

Data Index: 539771 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.3270. Min Act: -0.0000

Data Index: 131849 (C4 (Web Text))

Max Activating Token Index: 678

Text #6

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.3021. Min Act: -0.0000

Data Index: 1230180 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2827. Min Act: -0.0000

Data Index: 412468 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2683. Min Act: -0.0000

Data Index: 335398 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2733. Min Act: -0.0000

Data Index: 362087 (C4 (Web Text))

Max Activating Token Index: 345

Text #10

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2724. Min Act: -0.0000

Data Index: 1245610 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2911. Min Act: -0.0000

Data Index: 460768 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2666. Min Act: -0.0000

Data Index: 712781 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2559. Min Act: -0.0000

Data Index: 889176 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2461. Min Act: -0.0000

Data Index: 958765 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2535. Min Act: -0.0000

Data Index: 797553 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2509. Min Act: -0.0000

Data Index: 69934 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2507. Min Act: -0.0000

Data Index: 894171 (C4 (Web Text))

Max Activating Token Index: 497

Text #18

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2422. Min Act: -0.0000

Data Index: 950264 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2498. Min Act: -0.0000

Data Index: 736980 (C4 (Web Text))

Max Activating Token Index: 496