Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2937 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.5399. Min Act: -0.0000

Data Index: 1018127 (The Pile)

Max Activating Token Index: 41

Text #1

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.3469. Min Act: -0.0000

Data Index: 30562 (The Pile)

Max Activating Token Index: 590

Text #2

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.3600. Min Act: -0.0000

Data Index: 950210 (The Pile)

Max Activating Token Index: 726

Text #3

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.3487. Min Act: -0.0000

Data Index: 1787121 (The Pile)

Max Activating Token Index: 275

Text #4

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.3332. Min Act: -0.0000

Data Index: 655953 (The Pile)

Max Activating Token Index: 570

Text #5

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.3560. Min Act: -0.0000

Data Index: 1623699 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.3416. Min Act: -0.0000

Data Index: 1804493 (The Pile)

Max Activating Token Index: 944

Text #7

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.3425. Min Act: -0.0000

Data Index: 1695277 (The Pile)

Max Activating Token Index: 451

Text #8

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.3138. Min Act: -0.0000

Data Index: 1516536 (The Pile)

Max Activating Token Index: 379

Text #9

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.3327. Min Act: -0.0000

Data Index: 874893 (The Pile)

Max Activating Token Index: 103

Text #10

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.3300. Min Act: -0.0000

Data Index: 59894 (The Pile)

Max Activating Token Index: 240

Text #11

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.3214. Min Act: -0.0000

Data Index: 1104313 (The Pile)

Max Activating Token Index: 718

Text #12

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.3296. Min Act: -0.0000

Data Index: 1246934 (The Pile)

Max Activating Token Index: 814

Text #13

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.3097. Min Act: -0.0000

Data Index: 1436860 (The Pile)

Max Activating Token Index: 770

Text #14

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.3323. Min Act: -0.0000

Data Index: 1177836 (The Pile)

Max Activating Token Index: 142

Text #15

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.3311. Min Act: -0.0000

Data Index: 513979 (The Pile)

Max Activating Token Index: 285

Text #16

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.3127. Min Act: -0.0000

Data Index: 1784679 (The Pile)

Max Activating Token Index: 254

Text #17

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.3204. Min Act: -0.0000

Data Index: 209867 (The Pile)

Max Activating Token Index: 528

Text #18

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.3143. Min Act: -0.0000

Data Index: 562688 (The Pile)

Max Activating Token Index: 653

Text #19

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.3242. Min Act: -0.0000

Data Index: 177159 (The Pile)

Max Activating Token Index: 230