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

Dataset: The Pile

Neuron 4651 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4861. Min Act: -0.0000

Data Index: 1161966 (The Pile)

Max Activating Token Index: 154

Text #1

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4270. Min Act: -0.0000

Data Index: 192068 (The Pile)

Max Activating Token Index: 687

Text #2

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4020. Min Act: -0.0000

Data Index: 1565340 (The Pile)

Max Activating Token Index: 61

Text #3

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3765. Min Act: -0.0000

Data Index: 1083792 (The Pile)

Max Activating Token Index: 599

Text #4

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3665. Min Act: -0.0000

Data Index: 1997493 (The Pile)

Max Activating Token Index: 428

Text #5

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3714. Min Act: -0.0000

Data Index: 710095 (The Pile)

Max Activating Token Index: 455

Text #6

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4046. Min Act: -0.0000

Data Index: 1685480 (The Pile)

Max Activating Token Index: 1013

Text #7

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3645. Min Act: -0.0000

Data Index: 192152 (The Pile)

Max Activating Token Index: 750

Text #8

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3739. Min Act: -0.0000

Data Index: 1675711 (The Pile)

Max Activating Token Index: 140

Text #9

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4056. Min Act: -0.0000

Data Index: 1455027 (The Pile)

Max Activating Token Index: 703

Text #10

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3427. Min Act: -0.0000

Data Index: 833157 (The Pile)

Max Activating Token Index: 123

Text #11

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3755. Min Act: -0.0000

Data Index: 1423310 (The Pile)

Max Activating Token Index: 588

Text #12

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3340. Min Act: -0.0000

Data Index: 494237 (The Pile)

Max Activating Token Index: 569

Text #13

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3089. Min Act: -0.0000

Data Index: 1478916 (The Pile)

Max Activating Token Index: 905

Text #14

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3337. Min Act: -0.0000

Data Index: 17910 (The Pile)

Max Activating Token Index: 794

Text #15

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3526. Min Act: -0.0000

Data Index: 1633417 (The Pile)

Max Activating Token Index: 887

Text #16

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3388. Min Act: -0.0000

Data Index: 1551975 (The Pile)

Max Activating Token Index: 390

Text #17

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3473. Min Act: -0.0000

Data Index: 151579 (The Pile)

Max Activating Token Index: 264

Text #18

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3370. Min Act: -0.0000

Data Index: 485437 (The Pile)

Max Activating Token Index: 184

Text #19

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3246. Min Act: -0.0000

Data Index: 611411 (The Pile)

Max Activating Token Index: 922