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

Dataset: The Pile

Neuron 1857 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3001. Min Range: -1.3001

Max Act: 1.3001. Min Act: -0.0000

Data Index: 852400 (The Pile)

Max Activating Token Index: 1020

Text #1

Max Range: 1.3001. Min Range: -1.3001

Max Act: 0.9114. Min Act: -0.0000

Data Index: 899812 (The Pile)

Max Activating Token Index: 959

Text #2

Max Range: 1.3001. Min Range: -1.3001

Max Act: 0.9628. Min Act: -0.0000

Data Index: 1022040 (The Pile)

Max Activating Token Index: 571

Text #3

Max Range: 1.3001. Min Range: -1.3001

Max Act: 0.8511. Min Act: -0.0000

Data Index: 246719 (The Pile)

Max Activating Token Index: 171

Text #4

Max Range: 1.3001. Min Range: -1.3001

Max Act: 0.9378. Min Act: -0.0000

Data Index: 503410 (The Pile)

Max Activating Token Index: 421

Text #5

Max Range: 1.3001. Min Range: -1.3001

Max Act: 0.8384. Min Act: -0.0000

Data Index: 1423882 (The Pile)

Max Activating Token Index: 830

Text #6

Max Range: 1.3001. Min Range: -1.3001

Max Act: 0.8212. Min Act: -0.0000

Data Index: 1538427 (The Pile)

Max Activating Token Index: 20

Text #7

Max Range: 1.3001. Min Range: -1.3001

Max Act: 0.7896. Min Act: -0.0000

Data Index: 1667163 (The Pile)

Max Activating Token Index: 348

Text #8

Max Range: 1.3001. Min Range: -1.3001

Max Act: 0.8277. Min Act: -0.0000

Data Index: 993833 (The Pile)

Max Activating Token Index: 117

Text #9

Max Range: 1.3001. Min Range: -1.3001

Max Act: 0.8339. Min Act: -0.0000

Data Index: 1094508 (The Pile)

Max Activating Token Index: 322

Text #10

Max Range: 1.3001. Min Range: -1.3001

Max Act: 0.7260. Min Act: -0.0000

Data Index: 1450559 (The Pile)

Max Activating Token Index: 772

Text #11

Max Range: 1.3001. Min Range: -1.3001

Max Act: 0.7924. Min Act: -0.0000

Data Index: 1041704 (The Pile)

Max Activating Token Index: 215

Text #12

Max Range: 1.3001. Min Range: -1.3001

Max Act: 0.7493. Min Act: -0.0000

Data Index: 234802 (The Pile)

Max Activating Token Index: 195

Text #13

Max Range: 1.3001. Min Range: -1.3001

Max Act: 0.8514. Min Act: -0.0000

Data Index: 261590 (The Pile)

Max Activating Token Index: 26

Text #14

Max Range: 1.3001. Min Range: -1.3001

Max Act: 0.7263. Min Act: -0.0000

Data Index: 15943 (The Pile)

Max Activating Token Index: 187

Text #15

Max Range: 1.3001. Min Range: -1.3001

Max Act: 0.7038. Min Act: -0.0000

Data Index: 1587891 (The Pile)

Max Activating Token Index: 1019

Text #16

Max Range: 1.3001. Min Range: -1.3001

Max Act: 0.7485. Min Act: -0.0000

Data Index: 1982959 (The Pile)

Max Activating Token Index: 883

Text #17

Max Range: 1.3001. Min Range: -1.3001

Max Act: 0.7097. Min Act: -0.0000

Data Index: 1791279 (The Pile)

Max Activating Token Index: 249

Text #18

Max Range: 1.3001. Min Range: -1.3001

Max Act: 0.7414. Min Act: -0.0000

Data Index: 1966530 (The Pile)

Max Activating Token Index: 504

Text #19

Max Range: 1.3001. Min Range: -1.3001

Max Act: 0.7418. Min Act: -0.0000

Data Index: 477509 (The Pile)

Max Activating Token Index: 542