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

Dataset: The Pile

Neuron 3914 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: 1.9467. Min Range: -1.9467

Max Act: 1.9467. Min Act: -0.0000

Data Index: 832895 (The Pile)

Max Activating Token Index: 312

Text #1

Max Range: 1.9467. Min Range: -1.9467

Max Act: 1.7025. Min Act: -0.0000

Data Index: 1097187 (The Pile)

Max Activating Token Index: 392

Text #2

Max Range: 1.9467. Min Range: -1.9467

Max Act: 1.8206. Min Act: -0.0000

Data Index: 192500 (The Pile)

Max Activating Token Index: 205

Text #3

Max Range: 1.9467. Min Range: -1.9467

Max Act: 1.5582. Min Act: -0.0000

Data Index: 859479 (The Pile)

Max Activating Token Index: 434

Text #4

Max Range: 1.9467. Min Range: -1.9467

Max Act: 1.5582. Min Act: -0.0000

Data Index: 375259 (The Pile)

Max Activating Token Index: 428

Text #5

Max Range: 1.9467. Min Range: -1.9467

Max Act: 1.5557. Min Act: -0.0000

Data Index: 1329719 (The Pile)

Max Activating Token Index: 978

Text #6

Max Range: 1.9467. Min Range: -1.9467

Max Act: 1.5754. Min Act: -0.0000

Data Index: 553170 (The Pile)

Max Activating Token Index: 169

Text #7

Max Range: 1.9467. Min Range: -1.9467

Max Act: 1.4732. Min Act: -0.0000

Data Index: 585058 (The Pile)

Max Activating Token Index: 820

Text #8

Max Range: 1.9467. Min Range: -1.9467

Max Act: 1.3920. Min Act: -0.0000

Data Index: 1173337 (The Pile)

Max Activating Token Index: 527

Text #9

Max Range: 1.9467. Min Range: -1.9467

Max Act: 1.4614. Min Act: -0.0000

Data Index: 1751565 (The Pile)

Max Activating Token Index: 271

Text #10

Max Range: 1.9467. Min Range: -1.9467

Max Act: 1.3462. Min Act: -0.0000

Data Index: 1662025 (The Pile)

Max Activating Token Index: 109

Text #11

Max Range: 1.9467. Min Range: -1.9467

Max Act: 1.3463. Min Act: -0.0000

Data Index: 1990458 (The Pile)

Max Activating Token Index: 360

Text #12

Max Range: 1.9467. Min Range: -1.9467

Max Act: 1.3306. Min Act: -0.0000

Data Index: 1526496 (The Pile)

Max Activating Token Index: 761

Text #13

Max Range: 1.9467. Min Range: -1.9467

Max Act: 1.2893. Min Act: -0.0000

Data Index: 788447 (The Pile)

Max Activating Token Index: 979

Text #14

Max Range: 1.9467. Min Range: -1.9467

Max Act: 1.3624. Min Act: -0.0000

Data Index: 1581101 (The Pile)

Max Activating Token Index: 248

Text #15

Max Range: 1.9467. Min Range: -1.9467

Max Act: 1.3404. Min Act: -0.0000

Data Index: 1810300 (The Pile)

Max Activating Token Index: 570

Text #16

Max Range: 1.9467. Min Range: -1.9467

Max Act: 1.3408. Min Act: -0.0000

Data Index: 1428278 (The Pile)

Max Activating Token Index: 545

Text #17

Max Range: 1.9467. Min Range: -1.9467

Max Act: 1.2971. Min Act: -0.0000

Data Index: 577222 (The Pile)

Max Activating Token Index: 661

Text #18

Max Range: 1.9467. Min Range: -1.9467

Max Act: 1.2865. Min Act: -0.0000

Data Index: 432882 (The Pile)

Max Activating Token Index: 232

Text #19

Max Range: 1.9467. Min Range: -1.9467

Max Act: 1.2379. Min Act: -0.0000

Data Index: 823249 (The Pile)

Max Activating Token Index: 1019