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

Dataset: The Pile

Neuron 3483 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.5535. Min Act: -0.0000

Data Index: 556594 (The Pile)

Max Activating Token Index: 325

Text #1

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.5459. Min Act: -0.0000

Data Index: 310599 (The Pile)

Max Activating Token Index: 544

Text #2

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4979. Min Act: -0.0000

Data Index: 254992 (The Pile)

Max Activating Token Index: 414

Text #3

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.5282. Min Act: -0.0000

Data Index: 1079467 (The Pile)

Max Activating Token Index: 338

Text #4

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4959. Min Act: -0.0000

Data Index: 1847092 (The Pile)

Max Activating Token Index: 997

Text #5

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4671. Min Act: -0.0000

Data Index: 1352236 (The Pile)

Max Activating Token Index: 832

Text #6

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4823. Min Act: -0.0000

Data Index: 1631102 (The Pile)

Max Activating Token Index: 203

Text #7

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4040. Min Act: -0.0000

Data Index: 1821746 (The Pile)

Max Activating Token Index: 656

Text #8

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4710. Min Act: -0.0000

Data Index: 1415737 (The Pile)

Max Activating Token Index: 688

Text #9

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4318. Min Act: -0.0000

Data Index: 616014 (The Pile)

Max Activating Token Index: 849

Text #10

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4385. Min Act: -0.0000

Data Index: 1923233 (The Pile)

Max Activating Token Index: 242

Text #11

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4282. Min Act: -0.0000

Data Index: 1045244 (The Pile)

Max Activating Token Index: 756

Text #12

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4318. Min Act: -0.0000

Data Index: 222544 (The Pile)

Max Activating Token Index: 380

Text #13

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4380. Min Act: -0.0000

Data Index: 555942 (The Pile)

Max Activating Token Index: 453

Text #14

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4292. Min Act: -0.0000

Data Index: 981289 (The Pile)

Max Activating Token Index: 434

Text #15

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4215. Min Act: -0.0000

Data Index: 908425 (The Pile)

Max Activating Token Index: 255

Text #16

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4499. Min Act: -0.0000

Data Index: 283834 (The Pile)

Max Activating Token Index: 766

Text #17

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4040. Min Act: -0.0000

Data Index: 1177553 (The Pile)

Max Activating Token Index: 86

Text #18

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4187. Min Act: -0.0000

Data Index: 1222158 (The Pile)

Max Activating Token Index: 364

Text #19

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4361. Min Act: -0.0000

Data Index: 1695680 (The Pile)

Max Activating Token Index: 1007