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

Dataset: The Pile

Neuron 621 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: 0.5089. Min Range: -0.5089

Max Act: 0.5089. Min Act: -0.0000

Data Index: 1683451 (The Pile)

Max Activating Token Index: 365

Text #1

Max Range: 0.5089. Min Range: -0.5089

Max Act: 0.3581. Min Act: -0.0000

Data Index: 1029379 (The Pile)

Max Activating Token Index: 81

Text #2

Max Range: 0.5089. Min Range: -0.5089

Max Act: 0.3185. Min Act: -0.0000

Data Index: 1867991 (The Pile)

Max Activating Token Index: 698

Text #3

Max Range: 0.5089. Min Range: -0.5089

Max Act: 0.3219. Min Act: -0.0000

Data Index: 1970192 (The Pile)

Max Activating Token Index: 607

Text #4

Max Range: 0.5089. Min Range: -0.5089

Max Act: 0.3009. Min Act: -0.0000

Data Index: 1401390 (The Pile)

Max Activating Token Index: 931

Text #5

Max Range: 0.5089. Min Range: -0.5089

Max Act: 0.2961. Min Act: -0.0000

Data Index: 503282 (The Pile)

Max Activating Token Index: 270

Text #6

Max Range: 0.5089. Min Range: -0.5089

Max Act: 0.2878. Min Act: -0.0000

Data Index: 268005 (The Pile)

Max Activating Token Index: 590

Text #7

Max Range: 0.5089. Min Range: -0.5089

Max Act: 0.2834. Min Act: -0.0000

Data Index: 1406553 (The Pile)

Max Activating Token Index: 933

Text #8

Max Range: 0.5089. Min Range: -0.5089

Max Act: 0.2770. Min Act: -0.0000

Data Index: 454048 (The Pile)

Max Activating Token Index: 438

Text #9

Max Range: 0.5089. Min Range: -0.5089

Max Act: 0.2725. Min Act: -0.0000

Data Index: 72886 (The Pile)

Max Activating Token Index: 357

Text #10

Max Range: 0.5089. Min Range: -0.5089

Max Act: 0.2802. Min Act: -0.0000

Data Index: 611885 (The Pile)

Max Activating Token Index: 626

Text #11

Max Range: 0.5089. Min Range: -0.5089

Max Act: 0.2669. Min Act: -0.0000

Data Index: 151437 (The Pile)

Max Activating Token Index: 212

Text #12

Max Range: 0.5089. Min Range: -0.5089

Max Act: 0.2775. Min Act: -0.0000

Data Index: 417298 (The Pile)

Max Activating Token Index: 861

Text #13

Max Range: 0.5089. Min Range: -0.5089

Max Act: 0.2525. Min Act: -0.0000

Data Index: 972945 (The Pile)

Max Activating Token Index: 256

Text #14

Max Range: 0.5089. Min Range: -0.5089

Max Act: 0.2582. Min Act: -0.0000

Data Index: 1198485 (The Pile)

Max Activating Token Index: 320

Text #15

Max Range: 0.5089. Min Range: -0.5089

Max Act: 0.2572. Min Act: -0.0000

Data Index: 1571584 (The Pile)

Max Activating Token Index: 160

Text #16

Max Range: 0.5089. Min Range: -0.5089

Max Act: 0.2546. Min Act: -0.0000

Data Index: 758610 (The Pile)

Max Activating Token Index: 206

Text #17

Max Range: 0.5089. Min Range: -0.5089

Max Act: 0.2402. Min Act: -0.0000

Data Index: 1130961 (The Pile)

Max Activating Token Index: 15

Text #18

Max Range: 0.5089. Min Range: -0.5089

Max Act: 0.2727. Min Act: -0.0000

Data Index: 536170 (The Pile)

Max Activating Token Index: 442

Text #19

Max Range: 0.5089. Min Range: -0.5089

Max Act: 0.2519. Min Act: -0.0000

Data Index: 1894300 (The Pile)

Max Activating Token Index: 361