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

Dataset: The Pile

Neuron 4349 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.0297. Min Range: -1.0297

Max Act: 1.0193. Min Act: -0.0000

Data Index: 353376 (The Pile)

Max Activating Token Index: 402

Text #1

Max Range: 1.0297. Min Range: -1.0297

Max Act: 0.9036. Min Act: -0.0000

Data Index: 990574 (The Pile)

Max Activating Token Index: 137

Text #2

Max Range: 1.0297. Min Range: -1.0297

Max Act: 0.8510. Min Act: -0.0000

Data Index: 1394356 (The Pile)

Max Activating Token Index: 682

Text #3

Max Range: 1.0297. Min Range: -1.0297

Max Act: 1.0297. Min Act: -0.0000

Data Index: 1912443 (The Pile)

Max Activating Token Index: 965

Text #4

Max Range: 1.0297. Min Range: -1.0297

Max Act: 0.8533. Min Act: -0.0000

Data Index: 1719687 (The Pile)

Max Activating Token Index: 134

Text #5

Max Range: 1.0297. Min Range: -1.0297

Max Act: 0.9605. Min Act: -0.0000

Data Index: 1120789 (The Pile)

Max Activating Token Index: 133

Text #6

Max Range: 1.0297. Min Range: -1.0297

Max Act: 0.8323. Min Act: -0.0000

Data Index: 1238172 (The Pile)

Max Activating Token Index: 1018

Text #7

Max Range: 1.0297. Min Range: -1.0297

Max Act: 0.8787. Min Act: -0.0000

Data Index: 1651912 (The Pile)

Max Activating Token Index: 527

Text #8

Max Range: 1.0297. Min Range: -1.0297

Max Act: 0.8340. Min Act: -0.0000

Data Index: 1259504 (The Pile)

Max Activating Token Index: 965

Text #9

Max Range: 1.0297. Min Range: -1.0297

Max Act: 0.8618. Min Act: -0.0000

Data Index: 722878 (The Pile)

Max Activating Token Index: 892

Text #10

Max Range: 1.0297. Min Range: -1.0297

Max Act: 0.7417. Min Act: -0.0000

Data Index: 696677 (The Pile)

Max Activating Token Index: 821

Text #11

Max Range: 1.0297. Min Range: -1.0297

Max Act: 0.8093. Min Act: -0.0000

Data Index: 1992863 (The Pile)

Max Activating Token Index: 55

Text #12

Max Range: 1.0297. Min Range: -1.0297

Max Act: 0.7818. Min Act: -0.0000

Data Index: 87785 (The Pile)

Max Activating Token Index: 734

Text #13

Max Range: 1.0297. Min Range: -1.0297

Max Act: 0.8407. Min Act: -0.0000

Data Index: 1263522 (The Pile)

Max Activating Token Index: 722

Text #14

Max Range: 1.0297. Min Range: -1.0297

Max Act: 0.7607. Min Act: -0.0000

Data Index: 1302814 (The Pile)

Max Activating Token Index: 460

Text #15

Max Range: 1.0297. Min Range: -1.0297

Max Act: 0.8156. Min Act: -0.0000

Data Index: 248430 (The Pile)

Max Activating Token Index: 559

Text #16

Max Range: 1.0297. Min Range: -1.0297

Max Act: 0.7341. Min Act: -0.0000

Data Index: 811006 (The Pile)

Max Activating Token Index: 210

Text #17

Max Range: 1.0297. Min Range: -1.0297

Max Act: 0.7177. Min Act: -0.0000

Data Index: 651702 (The Pile)

Max Activating Token Index: 886

Text #18

Max Range: 1.0297. Min Range: -1.0297

Max Act: 0.6988. Min Act: -0.0000

Data Index: 1268481 (The Pile)

Max Activating Token Index: 167

Text #19

Max Range: 1.0297. Min Range: -1.0297

Max Act: 0.7817. Min Act: -0.0000

Data Index: 1555291 (The Pile)

Max Activating Token Index: 112