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

Dataset: The Pile

Neuron 938 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.3230. Min Act: -0.0000

Data Index: 1420735 (The Pile)

Max Activating Token Index: 814

Text #1

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.3125. Min Act: -0.0000

Data Index: 77076 (The Pile)

Max Activating Token Index: 420

Text #2

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2861. Min Act: -0.0000

Data Index: 128424 (The Pile)

Max Activating Token Index: 522

Text #3

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2890. Min Act: -0.0000

Data Index: 1354164 (The Pile)

Max Activating Token Index: 872

Text #4

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2784. Min Act: -0.0000

Data Index: 1892532 (The Pile)

Max Activating Token Index: 868

Text #5

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2868. Min Act: -0.0000

Data Index: 938610 (The Pile)

Max Activating Token Index: 974

Text #6

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2795. Min Act: -0.0000

Data Index: 1951358 (The Pile)

Max Activating Token Index: 149

Text #7

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2668. Min Act: -0.0000

Data Index: 493820 (The Pile)

Max Activating Token Index: 862

Text #8

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2572. Min Act: -0.0000

Data Index: 1837437 (The Pile)

Max Activating Token Index: 926

Text #9

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2644. Min Act: -0.0000

Data Index: 783424 (The Pile)

Max Activating Token Index: 158

Text #10

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2512. Min Act: -0.0000

Data Index: 1414713 (The Pile)

Max Activating Token Index: 953

Text #11

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2499. Min Act: -0.0000

Data Index: 662387 (The Pile)

Max Activating Token Index: 54

Text #12

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2557. Min Act: -0.0000

Data Index: 1060106 (The Pile)

Max Activating Token Index: 355

Text #13

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2446. Min Act: -0.0000

Data Index: 998433 (The Pile)

Max Activating Token Index: 864

Text #14

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2537. Min Act: -0.0000

Data Index: 1182617 (The Pile)

Max Activating Token Index: 338

Text #15

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2474. Min Act: -0.0000

Data Index: 450037 (The Pile)

Max Activating Token Index: 1022

Text #16

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2572. Min Act: -0.0000

Data Index: 273290 (The Pile)

Max Activating Token Index: 1021

Text #17

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2524. Min Act: -0.0000

Data Index: 1047776 (The Pile)

Max Activating Token Index: 937

Text #18

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2442. Min Act: -0.0000

Data Index: 594837 (The Pile)

Max Activating Token Index: 585

Text #19

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2527. Min Act: -0.0000

Data Index: 1520531 (The Pile)

Max Activating Token Index: 393