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

Dataset: The Pile

Neuron 611 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: 1.3447. Min Range: -1.3447

Max Act: 1.3447. Min Act: -0.0000

Data Index: 1599730 (The Pile)

Max Activating Token Index: 860

Text #1

Max Range: 1.3447. Min Range: -1.3447

Max Act: 1.2138. Min Act: -0.0000

Data Index: 1958436 (The Pile)

Max Activating Token Index: 299

Text #2

Max Range: 1.3447. Min Range: -1.3447

Max Act: 1.1144. Min Act: -0.0000

Data Index: 1571584 (The Pile)

Max Activating Token Index: 897

Text #3

Max Range: 1.3447. Min Range: -1.3447

Max Act: 1.1230. Min Act: -0.0000

Data Index: 607081 (The Pile)

Max Activating Token Index: 71

Text #4

Max Range: 1.3447. Min Range: -1.3447

Max Act: 1.0542. Min Act: -0.0000

Data Index: 858295 (The Pile)

Max Activating Token Index: 341

Text #5

Max Range: 1.3447. Min Range: -1.3447

Max Act: 1.1005. Min Act: -0.0000

Data Index: 1023780 (The Pile)

Max Activating Token Index: 371

Text #6

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.9224. Min Act: -0.0000

Data Index: 740247 (The Pile)

Max Activating Token Index: 73

Text #7

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.8429. Min Act: -0.0000

Data Index: 775506 (The Pile)

Max Activating Token Index: 740

Text #8

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.8869. Min Act: -0.0000

Data Index: 1749907 (The Pile)

Max Activating Token Index: 400

Text #9

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.8278. Min Act: -0.0000

Data Index: 1961010 (The Pile)

Max Activating Token Index: 282

Text #10

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.8467. Min Act: -0.0000

Data Index: 1275576 (The Pile)

Max Activating Token Index: 922

Text #11

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.6733. Min Act: -0.0000

Data Index: 201608 (The Pile)

Max Activating Token Index: 42

Text #12

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.7715. Min Act: -0.0000

Data Index: 105414 (The Pile)

Max Activating Token Index: 18

Text #13

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.8014. Min Act: -0.0000

Data Index: 1528067 (The Pile)

Max Activating Token Index: 70

Text #14

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.7758. Min Act: -0.0000

Data Index: 1993192 (The Pile)

Max Activating Token Index: 824

Text #15

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.7563. Min Act: -0.0000

Data Index: 1904561 (The Pile)

Max Activating Token Index: 28

Text #16

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.7163. Min Act: -0.0000

Data Index: 268828 (The Pile)

Max Activating Token Index: 259

Text #17

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.7262. Min Act: -0.0000

Data Index: 1051290 (The Pile)

Max Activating Token Index: 154

Text #18

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.7697. Min Act: -0.0000

Data Index: 415205 (The Pile)

Max Activating Token Index: 1007

Text #19

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.6771. Min Act: -0.0000

Data Index: 288267 (The Pile)

Max Activating Token Index: 382