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

Dataset: The Pile

Neuron 2768 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: 1.3815. Min Range: -1.3815

Max Act: 1.3349. Min Act: -0.0000

Data Index: 118447 (The Pile)

Max Activating Token Index: 467

Text #1

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.3588. Min Act: -0.0000

Data Index: 1346880 (The Pile)

Max Activating Token Index: 116

Text #2

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.2198. Min Act: -0.0000

Data Index: 1006666 (The Pile)

Max Activating Token Index: 647

Text #3

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.2749. Min Act: -0.0000

Data Index: 329560 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.1978. Min Act: -0.0000

Data Index: 1601045 (The Pile)

Max Activating Token Index: 303

Text #5

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.3815. Min Act: -0.0000

Data Index: 1519711 (The Pile)

Max Activating Token Index: 649

Text #6

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.2179. Min Act: -0.0000

Data Index: 1518966 (The Pile)

Max Activating Token Index: 306

Text #7

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.1313. Min Act: -0.0000

Data Index: 1600026 (The Pile)

Max Activating Token Index: 502

Text #8

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.2126. Min Act: -0.0000

Data Index: 1686809 (The Pile)

Max Activating Token Index: 731

Text #9

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.1335. Min Act: -0.0000

Data Index: 1004575 (The Pile)

Max Activating Token Index: 276

Text #10

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.0630. Min Act: -0.0000

Data Index: 567054 (The Pile)

Max Activating Token Index: 231

Text #11

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.0710. Min Act: -0.0000

Data Index: 1567866 (The Pile)

Max Activating Token Index: 717

Text #12

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.1204. Min Act: -0.0000

Data Index: 1879184 (The Pile)

Max Activating Token Index: 1009

Text #13

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.1218. Min Act: -0.0000

Data Index: 546535 (The Pile)

Max Activating Token Index: 382

Text #14

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.1704. Min Act: -0.0000

Data Index: 953984 (The Pile)

Max Activating Token Index: 857

Text #15

Max Range: 1.3815. Min Range: -1.3815

Max Act: 0.9948. Min Act: -0.0000

Data Index: 731556 (The Pile)

Max Activating Token Index: 573

Text #16

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.0951. Min Act: -0.0000

Data Index: 966607 (The Pile)

Max Activating Token Index: 673

Text #17

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.1213. Min Act: -0.0000

Data Index: 832099 (The Pile)

Max Activating Token Index: 560

Text #18

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.1212. Min Act: -0.0000

Data Index: 338735 (The Pile)

Max Activating Token Index: 667

Text #19

Max Range: 1.3815. Min Range: -1.3815

Max Act: 0.9966. Min Act: -0.0000

Data Index: 1071546 (The Pile)

Max Activating Token Index: 91