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

Dataset: The Pile

Neuron 2142 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: 0.2981. Min Range: -0.2981

Max Act: 0.2981. Min Act: -0.0000

Data Index: 910513 (The Pile)

Max Activating Token Index: 18

Text #1

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2873. Min Act: -0.0000

Data Index: 1550411 (The Pile)

Max Activating Token Index: 337

Text #2

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2694. Min Act: -0.0000

Data Index: 737175 (The Pile)

Max Activating Token Index: 177

Text #3

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2613. Min Act: -0.0000

Data Index: 1179541 (The Pile)

Max Activating Token Index: 26

Text #4

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2658. Min Act: -0.0000

Data Index: 1512653 (The Pile)

Max Activating Token Index: 151

Text #5

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2548. Min Act: -0.0000

Data Index: 901923 (The Pile)

Max Activating Token Index: 362

Text #6

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2405. Min Act: -0.0000

Data Index: 238525 (The Pile)

Max Activating Token Index: 399

Text #7

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2397. Min Act: -0.0000

Data Index: 1924058 (The Pile)

Max Activating Token Index: 294

Text #8

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2398. Min Act: -0.0000

Data Index: 404293 (The Pile)

Max Activating Token Index: 497

Text #9

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2355. Min Act: -0.0000

Data Index: 338910 (The Pile)

Max Activating Token Index: 994

Text #10

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2256. Min Act: -0.0000

Data Index: 690374 (The Pile)

Max Activating Token Index: 63

Text #11

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2315. Min Act: -0.0000

Data Index: 88633 (The Pile)

Max Activating Token Index: 372

Text #12

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2247. Min Act: -0.0000

Data Index: 1212151 (The Pile)

Max Activating Token Index: 588

Text #13

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2239. Min Act: -0.0000

Data Index: 673043 (The Pile)

Max Activating Token Index: 779

Text #14

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2192. Min Act: -0.0000

Data Index: 706407 (The Pile)

Max Activating Token Index: 787

Text #15

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2108. Min Act: -0.0000

Data Index: 997137 (The Pile)

Max Activating Token Index: 32

Text #16

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2027. Min Act: -0.0000

Data Index: 1713123 (The Pile)

Max Activating Token Index: 70

Text #17

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2087. Min Act: -0.0000

Data Index: 898102 (The Pile)

Max Activating Token Index: 530

Text #18

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2063. Min Act: -0.0000

Data Index: 1522136 (The Pile)

Max Activating Token Index: 651

Text #19

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2129. Min Act: -0.0000

Data Index: 1598710 (The Pile)

Max Activating Token Index: 102