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

Dataset: The Pile

Neuron 4016 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3471. Min Act: -0.0000

Data Index: 545032 (The Pile)

Max Activating Token Index: 757

Text #1

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3795. Min Act: -0.0000

Data Index: 2516 (The Pile)

Max Activating Token Index: 83

Text #2

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3233. Min Act: -0.0000

Data Index: 1214473 (The Pile)

Max Activating Token Index: 719

Text #3

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3822. Min Act: -0.0000

Data Index: 160547 (The Pile)

Max Activating Token Index: 87

Text #4

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3685. Min Act: -0.0000

Data Index: 1035821 (The Pile)

Max Activating Token Index: 452

Text #5

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3896. Min Act: -0.0000

Data Index: 1845782 (The Pile)

Max Activating Token Index: 104

Text #6

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3414. Min Act: -0.0000

Data Index: 824074 (The Pile)

Max Activating Token Index: 1022

Text #7

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3441. Min Act: -0.0000

Data Index: 526743 (The Pile)

Max Activating Token Index: 602

Text #8

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3618. Min Act: -0.0000

Data Index: 1107021 (The Pile)

Max Activating Token Index: 615

Text #9

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3881. Min Act: -0.0000

Data Index: 1680165 (The Pile)

Max Activating Token Index: 696

Text #10

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.4327. Min Act: -0.0000

Data Index: 1856101 (The Pile)

Max Activating Token Index: 781

Text #11

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3412. Min Act: -0.0000

Data Index: 1677043 (The Pile)

Max Activating Token Index: 1020

Text #12

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3283. Min Act: -0.0000

Data Index: 764702 (The Pile)

Max Activating Token Index: 224

Text #13

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3437. Min Act: -0.0000

Data Index: 1322633 (The Pile)

Max Activating Token Index: 207

Text #14

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3206. Min Act: -0.0000

Data Index: 1846404 (The Pile)

Max Activating Token Index: 215

Text #15

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3297. Min Act: -0.0000

Data Index: 1355182 (The Pile)

Max Activating Token Index: 336

Text #16

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3176. Min Act: -0.0000

Data Index: 153208 (The Pile)

Max Activating Token Index: 542

Text #17

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3407. Min Act: -0.0000

Data Index: 517275 (The Pile)

Max Activating Token Index: 161

Text #18

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3391. Min Act: -0.0000

Data Index: 532191 (The Pile)

Max Activating Token Index: 556

Text #19

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3388. Min Act: -0.0000

Data Index: 450636 (The Pile)

Max Activating Token Index: 121