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

Dataset: The Pile

Neuron 3623 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.3224. Min Act: -0.0000

Data Index: 1477102 (The Pile)

Max Activating Token Index: 606

Text #1

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.3109. Min Act: -0.0000

Data Index: 133823 (The Pile)

Max Activating Token Index: 375

Text #2

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.3177. Min Act: -0.0000

Data Index: 631720 (The Pile)

Max Activating Token Index: 656

Text #3

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2712. Min Act: -0.0000

Data Index: 294653 (The Pile)

Max Activating Token Index: 645

Text #4

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.3021. Min Act: -0.0000

Data Index: 1047155 (The Pile)

Max Activating Token Index: 535

Text #5

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2985. Min Act: -0.0001

Data Index: 457777 (The Pile)

Max Activating Token Index: 370

Text #6

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2841. Min Act: -0.0000

Data Index: 752927 (The Pile)

Max Activating Token Index: 627

Text #7

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2844. Min Act: -0.0000

Data Index: 1522405 (The Pile)

Max Activating Token Index: 364

Text #8

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2688. Min Act: -0.0000

Data Index: 227334 (The Pile)

Max Activating Token Index: 833

Text #9

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2663. Min Act: -0.0000

Data Index: 1498167 (The Pile)

Max Activating Token Index: 542

Text #10

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2704. Min Act: -0.0000

Data Index: 1702427 (The Pile)

Max Activating Token Index: 306

Text #11

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2582. Min Act: -0.0001

Data Index: 1363809 (The Pile)

Max Activating Token Index: 62

Text #12

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2712. Min Act: -0.0000

Data Index: 1226370 (The Pile)

Max Activating Token Index: 445

Text #13

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2780. Min Act: -0.0000

Data Index: 773873 (The Pile)

Max Activating Token Index: 636

Text #14

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2448. Min Act: -0.0000

Data Index: 1252012 (The Pile)

Max Activating Token Index: 581

Text #15

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2606. Min Act: -0.0001

Data Index: 349945 (The Pile)

Max Activating Token Index: 506

Text #16

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2422. Min Act: -0.0001

Data Index: 512314 (The Pile)

Max Activating Token Index: 185

Text #17

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2622. Min Act: -0.0000

Data Index: 623748 (The Pile)

Max Activating Token Index: 820

Text #18

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2533. Min Act: -0.0000

Data Index: 1190817 (The Pile)

Max Activating Token Index: 644

Text #19

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2523. Min Act: -0.0000

Data Index: 1772228 (The Pile)

Max Activating Token Index: 426