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

Dataset: The Pile

Neuron 846 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: 1.6262. Min Range: -1.6262

Max Act: 1.6262. Min Act: -0.0000

Data Index: 1747598 (The Pile)

Max Activating Token Index: 316

Text #1

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.2677. Min Act: -0.0000

Data Index: 1016340 (The Pile)

Max Activating Token Index: 567

Text #2

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.1906. Min Act: -0.0000

Data Index: 1989657 (The Pile)

Max Activating Token Index: 5

Text #3

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.0579. Min Act: -0.0000

Data Index: 716357 (The Pile)

Max Activating Token Index: 584

Text #4

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.1959. Min Act: -0.0000

Data Index: 177523 (The Pile)

Max Activating Token Index: 140

Text #5

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.1920. Min Act: -0.0000

Data Index: 885714 (The Pile)

Max Activating Token Index: 1010

Text #6

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.1484. Min Act: -0.0000

Data Index: 1735364 (The Pile)

Max Activating Token Index: 917

Text #7

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.1280. Min Act: -0.0000

Data Index: 861472 (The Pile)

Max Activating Token Index: 270

Text #8

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.1170. Min Act: -0.0000

Data Index: 1910299 (The Pile)

Max Activating Token Index: 304

Text #9

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.1141. Min Act: -0.0000

Data Index: 360294 (The Pile)

Max Activating Token Index: 178

Text #10

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.1290. Min Act: -0.0000

Data Index: 364053 (The Pile)

Max Activating Token Index: 784

Text #11

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.0690. Min Act: -0.0000

Data Index: 1133390 (The Pile)

Max Activating Token Index: 565

Text #12

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.0588. Min Act: -0.0000

Data Index: 309049 (The Pile)

Max Activating Token Index: 265

Text #13

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.0499. Min Act: -0.0000

Data Index: 1200859 (The Pile)

Max Activating Token Index: 636

Text #14

Max Range: 1.6262. Min Range: -1.6262

Max Act: 0.9804. Min Act: -0.0000

Data Index: 1900512 (The Pile)

Max Activating Token Index: 873

Text #15

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.0763. Min Act: -0.0000

Data Index: 1791162 (The Pile)

Max Activating Token Index: 538

Text #16

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.0914. Min Act: -0.0000

Data Index: 1973871 (The Pile)

Max Activating Token Index: 615

Text #17

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.0474. Min Act: -0.0000

Data Index: 229297 (The Pile)

Max Activating Token Index: 576

Text #18

Max Range: 1.6262. Min Range: -1.6262

Max Act: 0.9103. Min Act: -0.0000

Data Index: 483669 (The Pile)

Max Activating Token Index: 709

Text #19

Max Range: 1.6262. Min Range: -1.6262

Max Act: 0.9863. Min Act: -0.0000

Data Index: 1798239 (The Pile)

Max Activating Token Index: 251