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

Dataset: The Pile

Neuron 32 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 11.0330. Min Range: -11.0330

Max Act: 10.8120. Min Act: -0.0000

Data Index: 1796508 (The Pile)

Max Activating Token Index: 1010

Text #1

Max Range: 11.0330. Min Range: -11.0330

Max Act: 11.0330. Min Act: -0.0000

Data Index: 654269 (The Pile)

Max Activating Token Index: 464

Text #2

Max Range: 11.0330. Min Range: -11.0330

Max Act: 10.5942. Min Act: -0.0000

Data Index: 1059224 (The Pile)

Max Activating Token Index: 571

Text #3

Max Range: 11.0330. Min Range: -11.0330

Max Act: 9.9172. Min Act: -0.0000

Data Index: 24592 (The Pile)

Max Activating Token Index: 116

Text #4

Max Range: 11.0330. Min Range: -11.0330

Max Act: 10.2705. Min Act: -0.0000

Data Index: 1842697 (The Pile)

Max Activating Token Index: 110

Text #5

Max Range: 11.0330. Min Range: -11.0330

Max Act: 10.2396. Min Act: -0.0000

Data Index: 3782 (The Pile)

Max Activating Token Index: 935

Text #6

Max Range: 11.0330. Min Range: -11.0330

Max Act: 9.9976. Min Act: -0.0000

Data Index: 1102002 (The Pile)

Max Activating Token Index: 202

Text #7

Max Range: 11.0330. Min Range: -11.0330

Max Act: 10.2723. Min Act: -0.0000

Data Index: 1110382 (The Pile)

Max Activating Token Index: 135

Text #8

Max Range: 11.0330. Min Range: -11.0330

Max Act: 10.5506. Min Act: -0.0000

Data Index: 1090273 (The Pile)

Max Activating Token Index: 697

Text #9

Max Range: 11.0330. Min Range: -11.0330

Max Act: 10.2926. Min Act: -0.0000

Data Index: 1862222 (The Pile)

Max Activating Token Index: 930

Text #10

Max Range: 11.0330. Min Range: -11.0330

Max Act: 10.1773. Min Act: -0.0000

Data Index: 1975185 (The Pile)

Max Activating Token Index: 1012

Text #11

Max Range: 11.0330. Min Range: -11.0330

Max Act: 9.9266. Min Act: -0.0000

Data Index: 1161853 (The Pile)

Max Activating Token Index: 161

Text #12

Max Range: 11.0330. Min Range: -11.0330

Max Act: 9.9505. Min Act: -0.0000

Data Index: 1467331 (The Pile)

Max Activating Token Index: 256

Text #13

Max Range: 11.0330. Min Range: -11.0330

Max Act: 10.0469. Min Act: -0.0000

Data Index: 1764845 (The Pile)

Max Activating Token Index: 60

Text #14

Max Range: 11.0330. Min Range: -11.0330

Max Act: 10.1720. Min Act: -0.0000

Data Index: 1509130 (The Pile)

Max Activating Token Index: 170

Text #15

Max Range: 11.0330. Min Range: -11.0330

Max Act: 10.0038. Min Act: -0.0000

Data Index: 1899889 (The Pile)

Max Activating Token Index: 950

Text #16

Max Range: 11.0330. Min Range: -11.0330

Max Act: 10.0323. Min Act: -0.0000

Data Index: 1034228 (The Pile)

Max Activating Token Index: 744

Text #17

Max Range: 11.0330. Min Range: -11.0330

Max Act: 9.8576. Min Act: -0.0000

Data Index: 1259556 (The Pile)

Max Activating Token Index: 1013

Text #18

Max Range: 11.0330. Min Range: -11.0330

Max Act: 9.7169. Min Act: -0.0000

Data Index: 1386817 (The Pile)

Max Activating Token Index: 495

Text #19

Max Range: 11.0330. Min Range: -11.0330

Max Act: 9.6576. Min Act: -0.0000

Data Index: 1900962 (The Pile)

Max Activating Token Index: 335