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

Dataset: The Pile

Neuron 2851 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: 0.4397. Min Range: -0.4397

Max Act: 0.3873. Min Act: -0.0000

Data Index: 606496 (The Pile)

Max Activating Token Index: 285

Text #1

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.4397. Min Act: -0.0000

Data Index: 1986442 (The Pile)

Max Activating Token Index: 970

Text #2

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3819. Min Act: -0.0000

Data Index: 1936234 (The Pile)

Max Activating Token Index: 420

Text #3

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3668. Min Act: -0.0000

Data Index: 1873763 (The Pile)

Max Activating Token Index: 355

Text #4

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3455. Min Act: -0.0000

Data Index: 1202986 (The Pile)

Max Activating Token Index: 996

Text #5

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.4267. Min Act: -0.0000

Data Index: 605049 (The Pile)

Max Activating Token Index: 655

Text #6

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3276. Min Act: -0.0000

Data Index: 1026738 (The Pile)

Max Activating Token Index: 448

Text #7

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3385. Min Act: -0.0000

Data Index: 318420 (The Pile)

Max Activating Token Index: 845

Text #8

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3479. Min Act: -0.0000

Data Index: 1100622 (The Pile)

Max Activating Token Index: 581

Text #9

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3542. Min Act: -0.0000

Data Index: 703376 (The Pile)

Max Activating Token Index: 638

Text #10

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3204. Min Act: -0.0000

Data Index: 1748379 (The Pile)

Max Activating Token Index: 403

Text #11

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3359. Min Act: -0.0000

Data Index: 1473128 (The Pile)

Max Activating Token Index: 575

Text #12

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3181. Min Act: -0.0000

Data Index: 1544002 (The Pile)

Max Activating Token Index: 393

Text #13

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3456. Min Act: -0.0000

Data Index: 73314 (The Pile)

Max Activating Token Index: 862

Text #14

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3139. Min Act: -0.0000

Data Index: 1496454 (The Pile)

Max Activating Token Index: 976

Text #15

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3268. Min Act: -0.0000

Data Index: 1075437 (The Pile)

Max Activating Token Index: 394

Text #16

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3411. Min Act: -0.0000

Data Index: 311933 (The Pile)

Max Activating Token Index: 525

Text #17

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3416. Min Act: -0.0000

Data Index: 1717582 (The Pile)

Max Activating Token Index: 324

Text #18

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3101. Min Act: -0.0000

Data Index: 658048 (The Pile)

Max Activating Token Index: 460

Text #19

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3500. Min Act: -0.0000

Data Index: 1548300 (The Pile)

Max Activating Token Index: 1016