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

Dataset: The Pile

Neuron 3572 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1059. Min Range: -1.1059

Max Act: 1.1059. Min Act: -0.0000

Data Index: 53873 (The Pile)

Max Activating Token Index: 63

Text #1

Max Range: 1.1059. Min Range: -1.1059

Max Act: 1.0243. Min Act: -0.0000

Data Index: 1509937 (The Pile)

Max Activating Token Index: 92

Text #2

Max Range: 1.1059. Min Range: -1.1059

Max Act: 0.9538. Min Act: -0.0000

Data Index: 1937027 (The Pile)

Max Activating Token Index: 492

Text #3

Max Range: 1.1059. Min Range: -1.1059

Max Act: 1.0178. Min Act: -0.0000

Data Index: 1677368 (The Pile)

Max Activating Token Index: 357

Text #4

Max Range: 1.1059. Min Range: -1.1059

Max Act: 1.1036. Min Act: -0.0000

Data Index: 624418 (The Pile)

Max Activating Token Index: 920

Text #5

Max Range: 1.1059. Min Range: -1.1059

Max Act: 1.0077. Min Act: -0.0000

Data Index: 83012 (The Pile)

Max Activating Token Index: 213

Text #6

Max Range: 1.1059. Min Range: -1.1059

Max Act: 1.0084. Min Act: -0.0000

Data Index: 197723 (The Pile)

Max Activating Token Index: 384

Text #7

Max Range: 1.1059. Min Range: -1.1059

Max Act: 1.0252. Min Act: -0.0001

Data Index: 392620 (The Pile)

Max Activating Token Index: 401

Text #8

Max Range: 1.1059. Min Range: -1.1059

Max Act: 0.9916. Min Act: -0.0000

Data Index: 827444 (The Pile)

Max Activating Token Index: 514

Text #9

Max Range: 1.1059. Min Range: -1.1059

Max Act: 0.9509. Min Act: -0.0000

Data Index: 197856 (The Pile)

Max Activating Token Index: 89

Text #10

Max Range: 1.1059. Min Range: -1.1059

Max Act: 0.9558. Min Act: -0.0000

Data Index: 1633807 (The Pile)

Max Activating Token Index: 193

Text #11

Max Range: 1.1059. Min Range: -1.1059

Max Act: 0.9557. Min Act: -0.0000

Data Index: 1210588 (The Pile)

Max Activating Token Index: 153

Text #12

Max Range: 1.1059. Min Range: -1.1059

Max Act: 0.8490. Min Act: -0.0000

Data Index: 1620207 (The Pile)

Max Activating Token Index: 813

Text #13

Max Range: 1.1059. Min Range: -1.1059

Max Act: 0.9336. Min Act: -0.0000

Data Index: 1342503 (The Pile)

Max Activating Token Index: 654

Text #14

Max Range: 1.1059. Min Range: -1.1059

Max Act: 0.8922. Min Act: -0.0000

Data Index: 1178521 (The Pile)

Max Activating Token Index: 108

Text #15

Max Range: 1.1059. Min Range: -1.1059

Max Act: 0.8831. Min Act: -0.0000

Data Index: 1209596 (The Pile)

Max Activating Token Index: 339

Text #16

Max Range: 1.1059. Min Range: -1.1059

Max Act: 0.9419. Min Act: -0.0000

Data Index: 1340502 (The Pile)

Max Activating Token Index: 528

Text #17

Max Range: 1.1059. Min Range: -1.1059

Max Act: 0.8800. Min Act: -0.0000

Data Index: 700592 (The Pile)

Max Activating Token Index: 748

Text #18

Max Range: 1.1059. Min Range: -1.1059

Max Act: 0.9334. Min Act: -0.0000

Data Index: 556693 (The Pile)

Max Activating Token Index: 284

Text #19

Max Range: 1.1059. Min Range: -1.1059

Max Act: 0.7681. Min Act: -0.0000

Data Index: 1127522 (The Pile)

Max Activating Token Index: 906