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

Dataset: The Pile

Neuron 1560 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: 0.8763. Min Range: -0.8763

Max Act: 0.8763. Min Act: -0.0000

Data Index: 1945644 (The Pile)

Max Activating Token Index: 151

Text #1

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.8424. Min Act: -0.0000

Data Index: 386038 (The Pile)

Max Activating Token Index: 190

Text #2

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.8157. Min Act: -0.0000

Data Index: 634279 (The Pile)

Max Activating Token Index: 29

Text #3

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.7636. Min Act: -0.0000

Data Index: 1200773 (The Pile)

Max Activating Token Index: 485

Text #4

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.8132. Min Act: -0.0000

Data Index: 1140260 (The Pile)

Max Activating Token Index: 70

Text #5

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.7356. Min Act: 0.0001

Data Index: 868905 (The Pile)

Max Activating Token Index: 817

Text #6

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.7551. Min Act: -0.0000

Data Index: 705449 (The Pile)

Max Activating Token Index: 235

Text #7

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.7490. Min Act: -0.0000

Data Index: 1377658 (The Pile)

Max Activating Token Index: 304

Text #8

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.7275. Min Act: -0.0000

Data Index: 1094134 (The Pile)

Max Activating Token Index: 229

Text #9

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.6467. Min Act: -0.0000

Data Index: 733653 (The Pile)

Max Activating Token Index: 820

Text #10

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.7264. Min Act: -0.0000

Data Index: 619064 (The Pile)

Max Activating Token Index: 319

Text #11

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.7174. Min Act: -0.0000

Data Index: 1074328 (The Pile)

Max Activating Token Index: 1010

Text #12

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.7145. Min Act: -0.0000

Data Index: 837241 (The Pile)

Max Activating Token Index: 319

Text #13

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.7169. Min Act: -0.0000

Data Index: 972180 (The Pile)

Max Activating Token Index: 186

Text #14

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.7020. Min Act: -0.0000

Data Index: 1609293 (The Pile)

Max Activating Token Index: 476

Text #15

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.6880. Min Act: -0.0000

Data Index: 37318 (The Pile)

Max Activating Token Index: 527

Text #16

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.7234. Min Act: 0.0000

Data Index: 1435136 (The Pile)

Max Activating Token Index: 164

Text #17

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.6780. Min Act: -0.0000

Data Index: 1490573 (The Pile)

Max Activating Token Index: 543

Text #18

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.6432. Min Act: -0.0000

Data Index: 1475329 (The Pile)

Max Activating Token Index: 643

Text #19

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.6853. Min Act: -0.0000

Data Index: 131649 (The Pile)

Max Activating Token Index: 625