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

Dataset: The Pile

Neuron 1013 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: 1.5100. Min Range: -1.5100

Max Act: 1.5100. Min Act: -0.0000

Data Index: 1051729 (The Pile)

Max Activating Token Index: 248

Text #1

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.2656. Min Act: -0.0000

Data Index: 452162 (The Pile)

Max Activating Token Index: 78

Text #2

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.1573. Min Act: -0.0000

Data Index: 1164653 (The Pile)

Max Activating Token Index: 643

Text #3

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.2531. Min Act: -0.0000

Data Index: 159266 (The Pile)

Max Activating Token Index: 669

Text #4

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.1435. Min Act: -0.0000

Data Index: 1996561 (The Pile)

Max Activating Token Index: 696

Text #5

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.1605. Min Act: -0.0000

Data Index: 1875441 (The Pile)

Max Activating Token Index: 1002

Text #6

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.0452. Min Act: -0.0000

Data Index: 1043149 (The Pile)

Max Activating Token Index: 423

Text #7

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.1748. Min Act: -0.0000

Data Index: 1057873 (The Pile)

Max Activating Token Index: 224

Text #8

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.1373. Min Act: -0.0000

Data Index: 879354 (The Pile)

Max Activating Token Index: 311

Text #9

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.1231. Min Act: -0.0000

Data Index: 230704 (The Pile)

Max Activating Token Index: 489

Text #10

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.0854. Min Act: -0.0000

Data Index: 916766 (The Pile)

Max Activating Token Index: 354

Text #11

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.1092. Min Act: -0.0000

Data Index: 430994 (The Pile)

Max Activating Token Index: 454

Text #12

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.1166. Min Act: -0.0000

Data Index: 1561807 (The Pile)

Max Activating Token Index: 241

Text #13

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.1008. Min Act: -0.0000

Data Index: 105559 (The Pile)

Max Activating Token Index: 932

Text #14

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.0178. Min Act: -0.0000

Data Index: 402525 (The Pile)

Max Activating Token Index: 275

Text #15

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.0777. Min Act: -0.0000

Data Index: 1144679 (The Pile)

Max Activating Token Index: 189

Text #16

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.0467. Min Act: -0.0000

Data Index: 966749 (The Pile)

Max Activating Token Index: 709

Text #17

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.1031. Min Act: -0.0000

Data Index: 1745513 (The Pile)

Max Activating Token Index: 912

Text #18

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.0693. Min Act: -0.0000

Data Index: 1138917 (The Pile)

Max Activating Token Index: 372

Text #19

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.0896. Min Act: -0.0000

Data Index: 1474967 (The Pile)

Max Activating Token Index: 785