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

Dataset: The Pile

Neuron 2688 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.4453. Min Act: -0.0000

Data Index: 454123 (The Pile)

Max Activating Token Index: 731

Text #1

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3711. Min Act: -0.0000

Data Index: 736040 (The Pile)

Max Activating Token Index: 206

Text #2

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3609. Min Act: -0.0000

Data Index: 1621478 (The Pile)

Max Activating Token Index: 367

Text #3

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3663. Min Act: -0.0000

Data Index: 1281970 (The Pile)

Max Activating Token Index: 511

Text #4

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3427. Min Act: -0.0000

Data Index: 561633 (The Pile)

Max Activating Token Index: 589

Text #5

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3557. Min Act: -0.0000

Data Index: 1834404 (The Pile)

Max Activating Token Index: 1015

Text #6

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3495. Min Act: -0.0000

Data Index: 1732575 (The Pile)

Max Activating Token Index: 68

Text #7

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3292. Min Act: -0.0000

Data Index: 975292 (The Pile)

Max Activating Token Index: 320

Text #8

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3397. Min Act: -0.0000

Data Index: 1108532 (The Pile)

Max Activating Token Index: 842

Text #9

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3049. Min Act: -0.0000

Data Index: 1227989 (The Pile)

Max Activating Token Index: 132

Text #10

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3149. Min Act: -0.0000

Data Index: 672041 (The Pile)

Max Activating Token Index: 568

Text #11

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3650. Min Act: -0.0000

Data Index: 1651101 (The Pile)

Max Activating Token Index: 869

Text #12

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3291. Min Act: -0.0000

Data Index: 61864 (The Pile)

Max Activating Token Index: 188

Text #13

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3271. Min Act: -0.0000

Data Index: 795747 (The Pile)

Max Activating Token Index: 154

Text #14

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3264. Min Act: -0.0000

Data Index: 640883 (The Pile)

Max Activating Token Index: 410

Text #15

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3463. Min Act: -0.0000

Data Index: 495940 (The Pile)

Max Activating Token Index: 248

Text #16

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3195. Min Act: -0.0000

Data Index: 38699 (The Pile)

Max Activating Token Index: 707

Text #17

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3319. Min Act: -0.0000

Data Index: 1241857 (The Pile)

Max Activating Token Index: 748

Text #18

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3464. Min Act: -0.0000

Data Index: 1412213 (The Pile)

Max Activating Token Index: 676

Text #19

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3005. Min Act: -0.0000

Data Index: 1213481 (The Pile)

Max Activating Token Index: 597