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

Dataset: The Pile

Neuron 2229 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.6369. Min Act: -0.0000

Data Index: 691151 (The Pile)

Max Activating Token Index: 468

Text #1

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.6820. Min Act: -0.0000

Data Index: 1509454 (The Pile)

Max Activating Token Index: 980

Text #2

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.6767. Min Act: -0.0000

Data Index: 1473880 (The Pile)

Max Activating Token Index: 55

Text #3

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.6752. Min Act: -0.0000

Data Index: 69002 (The Pile)

Max Activating Token Index: 257

Text #4

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.5883. Min Act: -0.0000

Data Index: 808417 (The Pile)

Max Activating Token Index: 198

Text #5

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.6171. Min Act: 0.0000

Data Index: 571201 (The Pile)

Max Activating Token Index: 928

Text #6

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.6207. Min Act: -0.0000

Data Index: 1046173 (The Pile)

Max Activating Token Index: 177

Text #7

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.6144. Min Act: -0.0000

Data Index: 1080169 (The Pile)

Max Activating Token Index: 230

Text #8

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.5397. Min Act: -0.0000

Data Index: 1669430 (The Pile)

Max Activating Token Index: 531

Text #9

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.4948. Min Act: -0.0000

Data Index: 363197 (The Pile)

Max Activating Token Index: 789

Text #10

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.5006. Min Act: -0.0000

Data Index: 1946550 (The Pile)

Max Activating Token Index: 210

Text #11

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.5172. Min Act: -0.0000

Data Index: 1750786 (The Pile)

Max Activating Token Index: 251

Text #12

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.4849. Min Act: -0.0000

Data Index: 999469 (The Pile)

Max Activating Token Index: 253

Text #13

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.5083. Min Act: -0.0000

Data Index: 18090 (The Pile)

Max Activating Token Index: 699

Text #14

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.4926. Min Act: -0.0000

Data Index: 716731 (The Pile)

Max Activating Token Index: 1009

Text #15

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.5711. Min Act: -0.0000

Data Index: 1252767 (The Pile)

Max Activating Token Index: 90

Text #16

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.5015. Min Act: 0.0001

Data Index: 1664653 (The Pile)

Max Activating Token Index: 798

Text #17

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.4623. Min Act: -0.0000

Data Index: 1272892 (The Pile)

Max Activating Token Index: 686

Text #18

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.5019. Min Act: -0.0000

Data Index: 397082 (The Pile)

Max Activating Token Index: 246

Text #19

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.4732. Min Act: -0.0000

Data Index: 844367 (The Pile)

Max Activating Token Index: 642