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

Dataset: The Pile

Neuron 346 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: 1.6283. Min Range: -1.6283

Max Act: 1.6283. Min Act: -0.0000

Data Index: 145558 (The Pile)

Max Activating Token Index: 79

Text #1

Max Range: 1.6283. Min Range: -1.6283

Max Act: 1.4999. Min Act: -0.0000

Data Index: 1916071 (The Pile)

Max Activating Token Index: 892

Text #2

Max Range: 1.6283. Min Range: -1.6283

Max Act: 1.5505. Min Act: -0.0000

Data Index: 1013912 (The Pile)

Max Activating Token Index: 697

Text #3

Max Range: 1.6283. Min Range: -1.6283

Max Act: 1.4401. Min Act: -0.0000

Data Index: 1647778 (The Pile)

Max Activating Token Index: 386

Text #4

Max Range: 1.6283. Min Range: -1.6283

Max Act: 1.3882. Min Act: -0.0000

Data Index: 1215332 (The Pile)

Max Activating Token Index: 854

Text #5

Max Range: 1.6283. Min Range: -1.6283

Max Act: 1.2928. Min Act: -0.0000

Data Index: 286958 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 1.6283. Min Range: -1.6283

Max Act: 1.2330. Min Act: -0.0000

Data Index: 1819980 (The Pile)

Max Activating Token Index: 736

Text #7

Max Range: 1.6283. Min Range: -1.6283

Max Act: 1.1965. Min Act: -0.0000

Data Index: 535449 (The Pile)

Max Activating Token Index: 684

Text #8

Max Range: 1.6283. Min Range: -1.6283

Max Act: 1.3145. Min Act: -0.0000

Data Index: 1373297 (The Pile)

Max Activating Token Index: 469

Text #9

Max Range: 1.6283. Min Range: -1.6283

Max Act: 1.3201. Min Act: -0.0000

Data Index: 1269305 (The Pile)

Max Activating Token Index: 261

Text #10

Max Range: 1.6283. Min Range: -1.6283

Max Act: 1.3036. Min Act: -0.0000

Data Index: 1070048 (The Pile)

Max Activating Token Index: 601

Text #11

Max Range: 1.6283. Min Range: -1.6283

Max Act: 1.3005. Min Act: -0.0000

Data Index: 614253 (The Pile)

Max Activating Token Index: 938

Text #12

Max Range: 1.6283. Min Range: -1.6283

Max Act: 1.2063. Min Act: -0.0000

Data Index: 1622410 (The Pile)

Max Activating Token Index: 205

Text #13

Max Range: 1.6283. Min Range: -1.6283

Max Act: 1.2448. Min Act: -0.0000

Data Index: 935180 (The Pile)

Max Activating Token Index: 795

Text #14

Max Range: 1.6283. Min Range: -1.6283

Max Act: 1.3149. Min Act: -0.0000

Data Index: 592603 (The Pile)

Max Activating Token Index: 525

Text #15

Max Range: 1.6283. Min Range: -1.6283

Max Act: 1.1430. Min Act: -0.0000

Data Index: 725222 (The Pile)

Max Activating Token Index: 54

Text #16

Max Range: 1.6283. Min Range: -1.6283

Max Act: 1.2973. Min Act: -0.0000

Data Index: 571219 (The Pile)

Max Activating Token Index: 713

Text #17

Max Range: 1.6283. Min Range: -1.6283

Max Act: 1.2075. Min Act: -0.0000

Data Index: 958642 (The Pile)

Max Activating Token Index: 956

Text #18

Max Range: 1.6283. Min Range: -1.6283

Max Act: 1.2030. Min Act: -0.0000

Data Index: 1033843 (The Pile)

Max Activating Token Index: 16

Text #19

Max Range: 1.6283. Min Range: -1.6283

Max Act: 1.1945. Min Act: -0.0000

Data Index: 64071 (The Pile)

Max Activating Token Index: 678