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

Dataset: The Pile

Neuron 4875 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: 3.0930. Min Range: -3.0930

Max Act: 3.0930. Min Act: -0.0000

Data Index: 361965 (The Pile)

Max Activating Token Index: 281

Text #1

Max Range: 3.0930. Min Range: -3.0930

Max Act: 3.0133. Min Act: -0.0000

Data Index: 1846832 (The Pile)

Max Activating Token Index: 177

Text #2

Max Range: 3.0930. Min Range: -3.0930

Max Act: 2.5719. Min Act: -0.0000

Data Index: 855552 (The Pile)

Max Activating Token Index: 413

Text #3

Max Range: 3.0930. Min Range: -3.0930

Max Act: 2.4591. Min Act: -0.0000

Data Index: 1170096 (The Pile)

Max Activating Token Index: 285

Text #4

Max Range: 3.0930. Min Range: -3.0930

Max Act: 2.3879. Min Act: -0.0000

Data Index: 1331667 (The Pile)

Max Activating Token Index: 319

Text #5

Max Range: 3.0930. Min Range: -3.0930

Max Act: 1.8085. Min Act: -0.0000

Data Index: 1967738 (The Pile)

Max Activating Token Index: 923

Text #6

Max Range: 3.0930. Min Range: -3.0930

Max Act: 2.1575. Min Act: -0.0000

Data Index: 849072 (The Pile)

Max Activating Token Index: 375

Text #7

Max Range: 3.0930. Min Range: -3.0930

Max Act: 1.9938. Min Act: -0.0000

Data Index: 662598 (The Pile)

Max Activating Token Index: 592

Text #8

Max Range: 3.0930. Min Range: -3.0930

Max Act: 2.1964. Min Act: -0.0000

Data Index: 1296068 (The Pile)

Max Activating Token Index: 238

Text #9

Max Range: 3.0930. Min Range: -3.0930

Max Act: 1.9354. Min Act: -0.0000

Data Index: 1171394 (The Pile)

Max Activating Token Index: 351

Text #10

Max Range: 3.0930. Min Range: -3.0930

Max Act: 2.0232. Min Act: -0.0000

Data Index: 1028360 (The Pile)

Max Activating Token Index: 65

Text #11

Max Range: 3.0930. Min Range: -3.0930

Max Act: 2.0306. Min Act: -0.0000

Data Index: 535181 (The Pile)

Max Activating Token Index: 173

Text #12

Max Range: 3.0930. Min Range: -3.0930

Max Act: 1.9079. Min Act: -0.0000

Data Index: 223566 (The Pile)

Max Activating Token Index: 104

Text #13

Max Range: 3.0930. Min Range: -3.0930

Max Act: 1.5987. Min Act: -0.0000

Data Index: 924135 (The Pile)

Max Activating Token Index: 160

Text #14

Max Range: 3.0930. Min Range: -3.0930

Max Act: 1.7826. Min Act: -0.0000

Data Index: 1525337 (The Pile)

Max Activating Token Index: 537

Text #15

Max Range: 3.0930. Min Range: -3.0930

Max Act: 1.6706. Min Act: -0.0000

Data Index: 596996 (The Pile)

Max Activating Token Index: 566

Text #16

Max Range: 3.0930. Min Range: -3.0930

Max Act: 1.6830. Min Act: -0.0000

Data Index: 1925446 (The Pile)

Max Activating Token Index: 199

Text #17

Max Range: 3.0930. Min Range: -3.0930

Max Act: 1.6078. Min Act: -0.0000

Data Index: 1594291 (The Pile)

Max Activating Token Index: 612

Text #18

Max Range: 3.0930. Min Range: -3.0930

Max Act: 1.5361. Min Act: -0.0000

Data Index: 263110 (The Pile)

Max Activating Token Index: 187

Text #19

Max Range: 3.0930. Min Range: -3.0930

Max Act: 1.2591. Min Act: -0.0000

Data Index: 1438921 (The Pile)

Max Activating Token Index: 251