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

Dataset: The Pile

Neuron 3095 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: 0.5661. Min Range: -0.5661

Max Act: 0.5661. Min Act: -0.0000

Data Index: 1494610 (The Pile)

Max Activating Token Index: 35

Text #1

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.5025. Min Act: -0.0000

Data Index: 1164436 (The Pile)

Max Activating Token Index: 131

Text #2

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4811. Min Act: -0.0000

Data Index: 1526783 (The Pile)

Max Activating Token Index: 621

Text #3

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4892. Min Act: -0.0000

Data Index: 1457359 (The Pile)

Max Activating Token Index: 460

Text #4

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4397. Min Act: -0.0000

Data Index: 1334173 (The Pile)

Max Activating Token Index: 71

Text #5

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4226. Min Act: -0.0000

Data Index: 255967 (The Pile)

Max Activating Token Index: 948

Text #6

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3866. Min Act: -0.0000

Data Index: 585398 (The Pile)

Max Activating Token Index: 751

Text #7

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4109. Min Act: -0.0000

Data Index: 121951 (The Pile)

Max Activating Token Index: 245

Text #8

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3861. Min Act: -0.0000

Data Index: 966141 (The Pile)

Max Activating Token Index: 445

Text #9

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4086. Min Act: -0.0000

Data Index: 1120601 (The Pile)

Max Activating Token Index: 47

Text #10

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3810. Min Act: -0.0000

Data Index: 116648 (The Pile)

Max Activating Token Index: 575

Text #11

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4061. Min Act: -0.0000

Data Index: 664216 (The Pile)

Max Activating Token Index: 56

Text #12

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3610. Min Act: 0.0000

Data Index: 653184 (The Pile)

Max Activating Token Index: 135

Text #13

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3729. Min Act: -0.0000

Data Index: 393010 (The Pile)

Max Activating Token Index: 325

Text #14

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3722. Min Act: -0.0000

Data Index: 1047507 (The Pile)

Max Activating Token Index: 523

Text #15

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3333. Min Act: -0.0000

Data Index: 513102 (The Pile)

Max Activating Token Index: 670

Text #16

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3222. Min Act: -0.0000

Data Index: 1677072 (The Pile)

Max Activating Token Index: 121

Text #17

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3662. Min Act: -0.0000

Data Index: 369531 (The Pile)

Max Activating Token Index: 65

Text #18

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3512. Min Act: -0.0000

Data Index: 906190 (The Pile)

Max Activating Token Index: 259

Text #19

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3726. Min Act: 0.0000

Data Index: 852832 (The Pile)

Max Activating Token Index: 1004