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

Dataset: The Pile

Neuron 4070 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: 0.9333. Min Range: -0.9333

Max Act: 0.9120. Min Act: -0.0000

Data Index: 745380 (The Pile)

Max Activating Token Index: 1010

Text #1

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.9333. Min Act: -0.0000

Data Index: 217247 (The Pile)

Max Activating Token Index: 523

Text #2

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.8144. Min Act: -0.0000

Data Index: 436822 (The Pile)

Max Activating Token Index: 469

Text #3

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.8645. Min Act: -0.0000

Data Index: 1007217 (The Pile)

Max Activating Token Index: 454

Text #4

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.7949. Min Act: -0.0000

Data Index: 501579 (The Pile)

Max Activating Token Index: 56

Text #5

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.7699. Min Act: -0.0000

Data Index: 575350 (The Pile)

Max Activating Token Index: 91

Text #6

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.7590. Min Act: -0.0000

Data Index: 1220220 (The Pile)

Max Activating Token Index: 641

Text #7

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.7222. Min Act: -0.0000

Data Index: 1324298 (The Pile)

Max Activating Token Index: 213

Text #8

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.7446. Min Act: -0.0000

Data Index: 1626817 (The Pile)

Max Activating Token Index: 318

Text #9

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.7843. Min Act: -0.0000

Data Index: 1888885 (The Pile)

Max Activating Token Index: 153

Text #10

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.7583. Min Act: 0.0000

Data Index: 438299 (The Pile)

Max Activating Token Index: 156

Text #11

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.7553. Min Act: -0.0000

Data Index: 1314230 (The Pile)

Max Activating Token Index: 969

Text #12

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.7295. Min Act: -0.0000

Data Index: 1128059 (The Pile)

Max Activating Token Index: 900

Text #13

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.6803. Min Act: -0.0000

Data Index: 1913108 (The Pile)

Max Activating Token Index: 292

Text #14

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.6958. Min Act: -0.0000

Data Index: 1301946 (The Pile)

Max Activating Token Index: 262

Text #15

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.7120. Min Act: -0.0000

Data Index: 968393 (The Pile)

Max Activating Token Index: 221

Text #16

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.7041. Min Act: -0.0000

Data Index: 1374184 (The Pile)

Max Activating Token Index: 1010

Text #17

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.7257. Min Act: -0.0000

Data Index: 1967041 (The Pile)

Max Activating Token Index: 962

Text #18

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.6015. Min Act: -0.0000

Data Index: 838365 (The Pile)

Max Activating Token Index: 726

Text #19

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.6510. Min Act: -0.0000

Data Index: 1252039 (The Pile)

Max Activating Token Index: 779