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

Dataset: The Pile

Neuron 534 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7229. Min Range: -3.7229

Max Act: 3.6586. Min Act: -0.0000

Data Index: 159764 (The Pile)

Max Activating Token Index: 883

Text #1

Max Range: 3.7229. Min Range: -3.7229

Max Act: 3.6345. Min Act: -0.0000

Data Index: 1646816 (The Pile)

Max Activating Token Index: 364

Text #2

Max Range: 3.7229. Min Range: -3.7229

Max Act: 3.7229. Min Act: -0.0000

Data Index: 787020 (The Pile)

Max Activating Token Index: 86

Text #3

Max Range: 3.7229. Min Range: -3.7229

Max Act: 3.3751. Min Act: -0.0000

Data Index: 844806 (The Pile)

Max Activating Token Index: 884

Text #4

Max Range: 3.7229. Min Range: -3.7229

Max Act: 3.4040. Min Act: -0.0000

Data Index: 1078177 (The Pile)

Max Activating Token Index: 11

Text #5

Max Range: 3.7229. Min Range: -3.7229

Max Act: 3.5252. Min Act: -0.0000

Data Index: 687695 (The Pile)

Max Activating Token Index: 529

Text #6

Max Range: 3.7229. Min Range: -3.7229

Max Act: 3.2235. Min Act: -0.0000

Data Index: 1477149 (The Pile)

Max Activating Token Index: 687

Text #7

Max Range: 3.7229. Min Range: -3.7229

Max Act: 3.3423. Min Act: -0.0000

Data Index: 1680187 (The Pile)

Max Activating Token Index: 7

Text #8

Max Range: 3.7229. Min Range: -3.7229

Max Act: 3.1845. Min Act: -0.0000

Data Index: 509165 (The Pile)

Max Activating Token Index: 41

Text #9

Max Range: 3.7229. Min Range: -3.7229

Max Act: 3.2547. Min Act: -0.0000

Data Index: 1649672 (The Pile)

Max Activating Token Index: 20

Text #10

Max Range: 3.7229. Min Range: -3.7229

Max Act: 3.2219. Min Act: -0.0000

Data Index: 1119278 (The Pile)

Max Activating Token Index: 121

Text #11

Max Range: 3.7229. Min Range: -3.7229

Max Act: 3.0576. Min Act: -0.0000

Data Index: 1072657 (The Pile)

Max Activating Token Index: 345

Text #12

Max Range: 3.7229. Min Range: -3.7229

Max Act: 3.1942. Min Act: -0.0000

Data Index: 751962 (The Pile)

Max Activating Token Index: 902

Text #13

Max Range: 3.7229. Min Range: -3.7229

Max Act: 3.0332. Min Act: -0.0000

Data Index: 763301 (The Pile)

Max Activating Token Index: 505

Text #14

Max Range: 3.7229. Min Range: -3.7229

Max Act: 3.1539. Min Act: -0.0000

Data Index: 1946750 (The Pile)

Max Activating Token Index: 472

Text #15

Max Range: 3.7229. Min Range: -3.7229

Max Act: 3.0174. Min Act: -0.0000

Data Index: 1615866 (The Pile)

Max Activating Token Index: 204

Text #16

Max Range: 3.7229. Min Range: -3.7229

Max Act: 3.1378. Min Act: -0.0000

Data Index: 1958043 (The Pile)

Max Activating Token Index: 948

Text #17

Max Range: 3.7229. Min Range: -3.7229

Max Act: 2.8407. Min Act: -0.0000

Data Index: 1931933 (The Pile)

Max Activating Token Index: 713

Text #18

Max Range: 3.7229. Min Range: -3.7229

Max Act: 3.1294. Min Act: -0.0000

Data Index: 190596 (The Pile)

Max Activating Token Index: 378

Text #19

Max Range: 3.7229. Min Range: -3.7229

Max Act: 3.2202. Min Act: -0.0000

Data Index: 601795 (The Pile)

Max Activating Token Index: 912