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

Dataset: The Pile

Neuron 3269 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: 0.9716. Min Range: -0.9716

Max Act: 0.9716. Min Act: -0.0000

Data Index: 712108 (The Pile)

Max Activating Token Index: 726

Text #1

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.9190. Min Act: -0.0000

Data Index: 1494043 (The Pile)

Max Activating Token Index: 441

Text #2

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.9165. Min Act: -0.0000

Data Index: 239300 (The Pile)

Max Activating Token Index: 513

Text #3

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8997. Min Act: -0.0000

Data Index: 1847828 (The Pile)

Max Activating Token Index: 537

Text #4

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8982. Min Act: -0.0000

Data Index: 1965188 (The Pile)

Max Activating Token Index: 246

Text #5

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8664. Min Act: -0.0000

Data Index: 62025 (The Pile)

Max Activating Token Index: 431

Text #6

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8938. Min Act: -0.0000

Data Index: 588359 (The Pile)

Max Activating Token Index: 288

Text #7

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.9136. Min Act: -0.0000

Data Index: 692613 (The Pile)

Max Activating Token Index: 292

Text #8

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8479. Min Act: -0.0000

Data Index: 1884334 (The Pile)

Max Activating Token Index: 213

Text #9

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8333. Min Act: -0.0000

Data Index: 1088527 (The Pile)

Max Activating Token Index: 324

Text #10

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7914. Min Act: -0.0000

Data Index: 230648 (The Pile)

Max Activating Token Index: 124

Text #11

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8343. Min Act: -0.0000

Data Index: 1755744 (The Pile)

Max Activating Token Index: 925

Text #12

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8354. Min Act: -0.0000

Data Index: 1013021 (The Pile)

Max Activating Token Index: 390

Text #13

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8584. Min Act: -0.0000

Data Index: 984480 (The Pile)

Max Activating Token Index: 989

Text #14

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8128. Min Act: -0.0000

Data Index: 1290517 (The Pile)

Max Activating Token Index: 744

Text #15

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7889. Min Act: -0.0000

Data Index: 750181 (The Pile)

Max Activating Token Index: 202

Text #16

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8276. Min Act: -0.0000

Data Index: 1965890 (The Pile)

Max Activating Token Index: 574

Text #17

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8259. Min Act: -0.0000

Data Index: 1644732 (The Pile)

Max Activating Token Index: 25

Text #18

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8177. Min Act: -0.0000

Data Index: 1749972 (The Pile)

Max Activating Token Index: 197

Text #19

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8171. Min Act: -0.0000

Data Index: 1291394 (The Pile)

Max Activating Token Index: 1022