Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 12 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2154. Min Range: -1.2154

Max Act: 1.2154. Min Act: -0.0000

Data Index: 799871 (The Pile)

Max Activating Token Index: 971

Text #1

Max Range: 1.2154. Min Range: -1.2154

Max Act: 0.9550. Min Act: -0.0000

Data Index: 364542 (The Pile)

Max Activating Token Index: 458

Text #2

Max Range: 1.2154. Min Range: -1.2154

Max Act: 0.9991. Min Act: -0.0000

Data Index: 84575 (The Pile)

Max Activating Token Index: 178

Text #3

Max Range: 1.2154. Min Range: -1.2154

Max Act: 1.0146. Min Act: -0.0000

Data Index: 1377538 (The Pile)

Max Activating Token Index: 666

Text #4

Max Range: 1.2154. Min Range: -1.2154

Max Act: 0.9393. Min Act: -0.0000

Data Index: 801888 (The Pile)

Max Activating Token Index: 139

Text #5

Max Range: 1.2154. Min Range: -1.2154

Max Act: 0.9816. Min Act: -0.0000

Data Index: 486921 (The Pile)

Max Activating Token Index: 745

Text #6

Max Range: 1.2154. Min Range: -1.2154

Max Act: 0.8944. Min Act: -0.0000

Data Index: 1118270 (The Pile)

Max Activating Token Index: 125

Text #7

Max Range: 1.2154. Min Range: -1.2154

Max Act: 0.9657. Min Act: -0.0000

Data Index: 1676045 (The Pile)

Max Activating Token Index: 467

Text #8

Max Range: 1.2154. Min Range: -1.2154

Max Act: 0.9047. Min Act: -0.0000

Data Index: 912856 (The Pile)

Max Activating Token Index: 333

Text #9

Max Range: 1.2154. Min Range: -1.2154

Max Act: 0.9765. Min Act: -0.0000

Data Index: 283960 (The Pile)

Max Activating Token Index: 580

Text #10

Max Range: 1.2154. Min Range: -1.2154

Max Act: 0.9430. Min Act: -0.0000

Data Index: 1765479 (The Pile)

Max Activating Token Index: 610

Text #11

Max Range: 1.2154. Min Range: -1.2154

Max Act: 0.9383. Min Act: -0.0000

Data Index: 612842 (The Pile)

Max Activating Token Index: 203

Text #12

Max Range: 1.2154. Min Range: -1.2154

Max Act: 0.9360. Min Act: -0.0000

Data Index: 283074 (The Pile)

Max Activating Token Index: 849

Text #13

Max Range: 1.2154. Min Range: -1.2154

Max Act: 0.9349. Min Act: -0.0000

Data Index: 1581053 (The Pile)

Max Activating Token Index: 452

Text #14

Max Range: 1.2154. Min Range: -1.2154

Max Act: 0.9282. Min Act: -0.0000

Data Index: 932679 (The Pile)

Max Activating Token Index: 234

Text #15

Max Range: 1.2154. Min Range: -1.2154

Max Act: 0.9167. Min Act: -0.0000

Data Index: 724491 (The Pile)

Max Activating Token Index: 113

Text #16

Max Range: 1.2154. Min Range: -1.2154

Max Act: 0.9111. Min Act: -0.0000

Data Index: 1203298 (The Pile)

Max Activating Token Index: 327

Text #17

Max Range: 1.2154. Min Range: -1.2154

Max Act: 0.8911. Min Act: -0.0000

Data Index: 718744 (The Pile)

Max Activating Token Index: 374

Text #18

Max Range: 1.2154. Min Range: -1.2154

Max Act: 0.8400. Min Act: -0.0000

Data Index: 1311364 (The Pile)

Max Activating Token Index: 533

Text #19

Max Range: 1.2154. Min Range: -1.2154

Max Act: 0.9031. Min Act: -0.0000

Data Index: 1805477 (The Pile)

Max Activating Token Index: 797