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

Dataset: The Pile

Neuron 3700 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: 0.8195. Min Range: -0.8195

Max Act: 0.8195. Min Act: -0.0000

Data Index: 309026 (The Pile)

Max Activating Token Index: 1013

Text #1

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.7328. Min Act: -0.0000

Data Index: 950502 (The Pile)

Max Activating Token Index: 499

Text #2

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.7291. Min Act: -0.0000

Data Index: 649264 (The Pile)

Max Activating Token Index: 408

Text #3

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.7350. Min Act: -0.0000

Data Index: 1926672 (The Pile)

Max Activating Token Index: 726

Text #4

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.7004. Min Act: -0.0000

Data Index: 1820958 (The Pile)

Max Activating Token Index: 565

Text #5

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.7434. Min Act: -0.0000

Data Index: 87176 (The Pile)

Max Activating Token Index: 815

Text #6

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.7190. Min Act: -0.0000

Data Index: 685252 (The Pile)

Max Activating Token Index: 339

Text #7

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.6925. Min Act: -0.0000

Data Index: 1640629 (The Pile)

Max Activating Token Index: 591

Text #8

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.6912. Min Act: -0.0000

Data Index: 431762 (The Pile)

Max Activating Token Index: 397

Text #9

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.7031. Min Act: -0.0000

Data Index: 486787 (The Pile)

Max Activating Token Index: 821

Text #10

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.6601. Min Act: -0.0000

Data Index: 1398988 (The Pile)

Max Activating Token Index: 808

Text #11

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.6397. Min Act: -0.0000

Data Index: 1702202 (The Pile)

Max Activating Token Index: 115

Text #12

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.7226. Min Act: -0.0000

Data Index: 141953 (The Pile)

Max Activating Token Index: 45

Text #13

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.6496. Min Act: -0.0000

Data Index: 206767 (The Pile)

Max Activating Token Index: 303

Text #14

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.6385. Min Act: -0.0000

Data Index: 355402 (The Pile)

Max Activating Token Index: 869

Text #15

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.6527. Min Act: -0.0000

Data Index: 1863139 (The Pile)

Max Activating Token Index: 683

Text #16

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.6533. Min Act: -0.0000

Data Index: 261245 (The Pile)

Max Activating Token Index: 731

Text #17

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.6730. Min Act: -0.0000

Data Index: 1467459 (The Pile)

Max Activating Token Index: 261

Text #18

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.6461. Min Act: -0.0000

Data Index: 213355 (The Pile)

Max Activating Token Index: 661

Text #19

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.6667. Min Act: -0.0000

Data Index: 1837115 (The Pile)

Max Activating Token Index: 19