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

Dataset: The Pile

Neuron 60 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: 1.4451. Min Range: -1.4451

Max Act: 1.4451. Min Act: -0.0000

Data Index: 569895 (The Pile)

Max Activating Token Index: 36

Text #1

Max Range: 1.4451. Min Range: -1.4451

Max Act: 0.7206. Min Act: -0.0000

Data Index: 1119552 (The Pile)

Max Activating Token Index: 146

Text #2

Max Range: 1.4451. Min Range: -1.4451

Max Act: 0.9724. Min Act: -0.0000

Data Index: 1845973 (The Pile)

Max Activating Token Index: 353

Text #3

Max Range: 1.4451. Min Range: -1.4451

Max Act: 0.5962. Min Act: -0.0000

Data Index: 27216 (The Pile)

Max Activating Token Index: 347

Text #4

Max Range: 1.4451. Min Range: -1.4451

Max Act: 0.6367. Min Act: -0.0000

Data Index: 103574 (The Pile)

Max Activating Token Index: 934

Text #5

Max Range: 1.4451. Min Range: -1.4451

Max Act: 0.4664. Min Act: -0.0000

Data Index: 1370381 (The Pile)

Max Activating Token Index: 209

Text #6

Max Range: 1.4451. Min Range: -1.4451

Max Act: 0.3813. Min Act: -0.0000

Data Index: 1592143 (The Pile)

Max Activating Token Index: 900

Text #7

Max Range: 1.4451. Min Range: -1.4451

Max Act: 0.2401. Min Act: -0.0000

Data Index: 1494879 (The Pile)

Max Activating Token Index: 987

Text #8

Max Range: 1.4451. Min Range: -1.4451

Max Act: 0.2830. Min Act: -0.0000

Data Index: 1958678 (The Pile)

Max Activating Token Index: 839

Text #9

Max Range: 1.4451. Min Range: -1.4451

Max Act: 0.2371. Min Act: -0.0000

Data Index: 1540823 (The Pile)

Max Activating Token Index: 556

Text #10

Max Range: 1.4451. Min Range: -1.4451

Max Act: 0.2300. Min Act: -0.0000

Data Index: 560381 (The Pile)

Max Activating Token Index: 1004

Text #11

Max Range: 1.4451. Min Range: -1.4451

Max Act: 0.3055. Min Act: -0.0000

Data Index: 167653 (The Pile)

Max Activating Token Index: 477

Text #12

Max Range: 1.4451. Min Range: -1.4451

Max Act: 0.2781. Min Act: -0.0000

Data Index: 926194 (The Pile)

Max Activating Token Index: 767

Text #13

Max Range: 1.4451. Min Range: -1.4451

Max Act: 0.2451. Min Act: -0.0000

Data Index: 1724515 (The Pile)

Max Activating Token Index: 823

Text #14

Max Range: 1.4451. Min Range: -1.4451

Max Act: 0.2830. Min Act: -0.0000

Data Index: 1411709 (The Pile)

Max Activating Token Index: 849

Text #15

Max Range: 1.4451. Min Range: -1.4451

Max Act: 0.2218. Min Act: -0.0000

Data Index: 1138217 (The Pile)

Max Activating Token Index: 876

Text #16

Max Range: 1.4451. Min Range: -1.4451

Max Act: 0.2552. Min Act: -0.0000

Data Index: 1990184 (The Pile)

Max Activating Token Index: 852

Text #17

Max Range: 1.4451. Min Range: -1.4451

Max Act: 0.2175. Min Act: -0.0000

Data Index: 925164 (The Pile)

Max Activating Token Index: 387

Text #18

Max Range: 1.4451. Min Range: -1.4451

Max Act: 0.2110. Min Act: -0.0000

Data Index: 983749 (The Pile)

Max Activating Token Index: 238

Text #19

Max Range: 1.4451. Min Range: -1.4451

Max Act: 0.2163. Min Act: -0.0000

Data Index: 854999 (The Pile)

Max Activating Token Index: 441