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

Dataset: The Pile

Neuron 1446 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: 1.7413. Min Range: -1.7413

Max Act: 1.6974. Min Act: -0.0000

Data Index: 1887317 (The Pile)

Max Activating Token Index: 31

Text #1

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.6401. Min Act: -0.0000

Data Index: 1193752 (The Pile)

Max Activating Token Index: 147

Text #2

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.7413. Min Act: -0.0000

Data Index: 1833351 (The Pile)

Max Activating Token Index: 764

Text #3

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.4284. Min Act: -0.0000

Data Index: 1019043 (The Pile)

Max Activating Token Index: 511

Text #4

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.5873. Min Act: -0.0000

Data Index: 889619 (The Pile)

Max Activating Token Index: 923

Text #5

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.5284. Min Act: -0.0000

Data Index: 1094698 (The Pile)

Max Activating Token Index: 611

Text #6

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.4640. Min Act: -0.0000

Data Index: 1203753 (The Pile)

Max Activating Token Index: 16

Text #7

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.4601. Min Act: -0.0000

Data Index: 1214425 (The Pile)

Max Activating Token Index: 321

Text #8

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.4833. Min Act: -0.0000

Data Index: 1435365 (The Pile)

Max Activating Token Index: 471

Text #9

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.3524. Min Act: -0.0000

Data Index: 1270263 (The Pile)

Max Activating Token Index: 602

Text #10

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.3946. Min Act: -0.0000

Data Index: 1699190 (The Pile)

Max Activating Token Index: 409

Text #11

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.3419. Min Act: -0.0000

Data Index: 1030391 (The Pile)

Max Activating Token Index: 668

Text #12

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.2857. Min Act: -0.0000

Data Index: 598054 (The Pile)

Max Activating Token Index: 575

Text #13

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.3187. Min Act: -0.0000

Data Index: 1082822 (The Pile)

Max Activating Token Index: 160

Text #14

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.3459. Min Act: -0.0000

Data Index: 890837 (The Pile)

Max Activating Token Index: 365

Text #15

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.3991. Min Act: -0.0000

Data Index: 696 (The Pile)

Max Activating Token Index: 118

Text #16

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.3297. Min Act: -0.0000

Data Index: 668467 (The Pile)

Max Activating Token Index: 41

Text #17

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.3149. Min Act: -0.0001

Data Index: 373603 (The Pile)

Max Activating Token Index: 49

Text #18

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.3085. Min Act: -0.0000

Data Index: 484773 (The Pile)

Max Activating Token Index: 239

Text #19

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.2315. Min Act: -0.0000

Data Index: 340846 (The Pile)

Max Activating Token Index: 359