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

Dataset: The Pile

Neuron 31 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: 1.3132. Min Range: -1.3132

Max Act: 1.3132. Min Act: -0.0000

Data Index: 772924 (The Pile)

Max Activating Token Index: 893

Text #1

Max Range: 1.3132. Min Range: -1.3132

Max Act: 1.2292. Min Act: -0.0000

Data Index: 362637 (The Pile)

Max Activating Token Index: 253

Text #2

Max Range: 1.3132. Min Range: -1.3132

Max Act: 1.1979. Min Act: -0.0000

Data Index: 516959 (The Pile)

Max Activating Token Index: 437

Text #3

Max Range: 1.3132. Min Range: -1.3132

Max Act: 1.1764. Min Act: -0.0000

Data Index: 1272668 (The Pile)

Max Activating Token Index: 612

Text #4

Max Range: 1.3132. Min Range: -1.3132

Max Act: 1.2060. Min Act: -0.0000

Data Index: 1217236 (The Pile)

Max Activating Token Index: 901

Text #5

Max Range: 1.3132. Min Range: -1.3132

Max Act: 0.9128. Min Act: -0.0000

Data Index: 969100 (The Pile)

Max Activating Token Index: 91

Text #6

Max Range: 1.3132. Min Range: -1.3132

Max Act: 1.0563. Min Act: -0.0000

Data Index: 1835030 (The Pile)

Max Activating Token Index: 741

Text #7

Max Range: 1.3132. Min Range: -1.3132

Max Act: 1.1059. Min Act: -0.0000

Data Index: 1576761 (The Pile)

Max Activating Token Index: 537

Text #8

Max Range: 1.3132. Min Range: -1.3132

Max Act: 1.1079. Min Act: -0.0000

Data Index: 1891788 (The Pile)

Max Activating Token Index: 445

Text #9

Max Range: 1.3132. Min Range: -1.3132

Max Act: 1.0427. Min Act: -0.0000

Data Index: 540157 (The Pile)

Max Activating Token Index: 149

Text #10

Max Range: 1.3132. Min Range: -1.3132

Max Act: 1.0561. Min Act: -0.0000

Data Index: 1907404 (The Pile)

Max Activating Token Index: 96

Text #11

Max Range: 1.3132. Min Range: -1.3132

Max Act: 1.0875. Min Act: -0.0000

Data Index: 1274062 (The Pile)

Max Activating Token Index: 131

Text #12

Max Range: 1.3132. Min Range: -1.3132

Max Act: 1.0720. Min Act: -0.0000

Data Index: 670230 (The Pile)

Max Activating Token Index: 742

Text #13

Max Range: 1.3132. Min Range: -1.3132

Max Act: 1.0681. Min Act: -0.0000

Data Index: 1473869 (The Pile)

Max Activating Token Index: 112

Text #14

Max Range: 1.3132. Min Range: -1.3132

Max Act: 1.0066. Min Act: -0.0000

Data Index: 1460735 (The Pile)

Max Activating Token Index: 808

Text #15

Max Range: 1.3132. Min Range: -1.3132

Max Act: 1.1485. Min Act: -0.0000

Data Index: 1062218 (The Pile)

Max Activating Token Index: 971

Text #16

Max Range: 1.3132. Min Range: -1.3132

Max Act: 1.0318. Min Act: -0.0000

Data Index: 307375 (The Pile)

Max Activating Token Index: 108

Text #17

Max Range: 1.3132. Min Range: -1.3132

Max Act: 1.0965. Min Act: -0.0000

Data Index: 928129 (The Pile)

Max Activating Token Index: 41

Text #18

Max Range: 1.3132. Min Range: -1.3132

Max Act: 0.9933. Min Act: -0.0000

Data Index: 306042 (The Pile)

Max Activating Token Index: 254

Text #19

Max Range: 1.3132. Min Range: -1.3132

Max Act: 0.9763. Min Act: -0.0000

Data Index: 457211 (The Pile)

Max Activating Token Index: 1015