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

Dataset: The Pile

Neuron 3684 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2681. Min Act: -0.0000

Data Index: 1888153 (The Pile)

Max Activating Token Index: 801

Text #1

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.3420. Min Act: -0.0000

Data Index: 13979 (The Pile)

Max Activating Token Index: 356

Text #2

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.3512. Min Act: -0.0000

Data Index: 835884 (The Pile)

Max Activating Token Index: 899

Text #3

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.3171. Min Act: -0.0000

Data Index: 130195 (The Pile)

Max Activating Token Index: 755

Text #4

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2887. Min Act: -0.0000

Data Index: 335507 (The Pile)

Max Activating Token Index: 543

Text #5

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.3610. Min Act: -0.0000

Data Index: 138347 (The Pile)

Max Activating Token Index: 639

Text #6

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.3583. Min Act: -0.0000

Data Index: 1851328 (The Pile)

Max Activating Token Index: 680

Text #7

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.3603. Min Act: -0.0000

Data Index: 942735 (The Pile)

Max Activating Token Index: 534

Text #8

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.3214. Min Act: 0.0000

Data Index: 1543028 (The Pile)

Max Activating Token Index: 70

Text #9

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.3101. Min Act: -0.0000

Data Index: 1269625 (The Pile)

Max Activating Token Index: 503

Text #10

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.3247. Min Act: 0.0000

Data Index: 542087 (The Pile)

Max Activating Token Index: 353

Text #11

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.3148. Min Act: -0.0000

Data Index: 829149 (The Pile)

Max Activating Token Index: 776

Text #12

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2964. Min Act: -0.0000

Data Index: 474686 (The Pile)

Max Activating Token Index: 567

Text #13

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2916. Min Act: -0.0000

Data Index: 1979982 (The Pile)

Max Activating Token Index: 686

Text #14

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.3085. Min Act: -0.0000

Data Index: 630430 (The Pile)

Max Activating Token Index: 250

Text #15

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.3250. Min Act: -0.0000

Data Index: 1909916 (The Pile)

Max Activating Token Index: 372

Text #16

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.3447. Min Act: -0.0000

Data Index: 1679032 (The Pile)

Max Activating Token Index: 816

Text #17

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.3057. Min Act: -0.0000

Data Index: 21592 (The Pile)

Max Activating Token Index: 319

Text #18

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2900. Min Act: -0.0000

Data Index: 872053 (The Pile)

Max Activating Token Index: 576

Text #19

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.3018. Min Act: -0.0000

Data Index: 12495 (The Pile)

Max Activating Token Index: 539