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

Dataset: The Pile

Neuron 3838 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: 1.1261. Min Range: -1.1261

Max Act: 1.1261. Min Act: -0.0000

Data Index: 299436 (The Pile)

Max Activating Token Index: 46

Text #1

Max Range: 1.1261. Min Range: -1.1261

Max Act: 1.1244. Min Act: -0.0000

Data Index: 1504703 (The Pile)

Max Activating Token Index: 173

Text #2

Max Range: 1.1261. Min Range: -1.1261

Max Act: 1.0999. Min Act: -0.0000

Data Index: 1732730 (The Pile)

Max Activating Token Index: 912

Text #3

Max Range: 1.1261. Min Range: -1.1261

Max Act: 0.9869. Min Act: -0.0000

Data Index: 352010 (The Pile)

Max Activating Token Index: 576

Text #4

Max Range: 1.1261. Min Range: -1.1261

Max Act: 1.0139. Min Act: -0.0000

Data Index: 1108831 (The Pile)

Max Activating Token Index: 20

Text #5

Max Range: 1.1261. Min Range: -1.1261

Max Act: 0.9077. Min Act: -0.0000

Data Index: 1189859 (The Pile)

Max Activating Token Index: 879

Text #6

Max Range: 1.1261. Min Range: -1.1261

Max Act: 0.9322. Min Act: -0.0000

Data Index: 1671339 (The Pile)

Max Activating Token Index: 22

Text #7

Max Range: 1.1261. Min Range: -1.1261

Max Act: 0.9181. Min Act: -0.0000

Data Index: 1932908 (The Pile)

Max Activating Token Index: 622

Text #8

Max Range: 1.1261. Min Range: -1.1261

Max Act: 0.9212. Min Act: -0.0000

Data Index: 1393352 (The Pile)

Max Activating Token Index: 881

Text #9

Max Range: 1.1261. Min Range: -1.1261

Max Act: 0.9513. Min Act: -0.0000

Data Index: 409348 (The Pile)

Max Activating Token Index: 547

Text #10

Max Range: 1.1261. Min Range: -1.1261

Max Act: 0.9678. Min Act: -0.0000

Data Index: 1730005 (The Pile)

Max Activating Token Index: 632

Text #11

Max Range: 1.1261. Min Range: -1.1261

Max Act: 0.9725. Min Act: -0.0000

Data Index: 416700 (The Pile)

Max Activating Token Index: 730

Text #12

Max Range: 1.1261. Min Range: -1.1261

Max Act: 0.9085. Min Act: -0.0000

Data Index: 1459605 (The Pile)

Max Activating Token Index: 84

Text #13

Max Range: 1.1261. Min Range: -1.1261

Max Act: 0.9098. Min Act: -0.0000

Data Index: 597758 (The Pile)

Max Activating Token Index: 45

Text #14

Max Range: 1.1261. Min Range: -1.1261

Max Act: 0.9474. Min Act: -0.0000

Data Index: 208753 (The Pile)

Max Activating Token Index: 178

Text #15

Max Range: 1.1261. Min Range: -1.1261

Max Act: 0.9823. Min Act: -0.0000

Data Index: 405570 (The Pile)

Max Activating Token Index: 376

Text #16

Max Range: 1.1261. Min Range: -1.1261

Max Act: 0.9440. Min Act: -0.0000

Data Index: 535584 (The Pile)

Max Activating Token Index: 659

Text #17

Max Range: 1.1261. Min Range: -1.1261

Max Act: 0.9859. Min Act: -0.0000

Data Index: 1516773 (The Pile)

Max Activating Token Index: 935

Text #18

Max Range: 1.1261. Min Range: -1.1261

Max Act: 0.9240. Min Act: -0.0000

Data Index: 888899 (The Pile)

Max Activating Token Index: 720

Text #19

Max Range: 1.1261. Min Range: -1.1261

Max Act: 0.9124. Min Act: -0.0000

Data Index: 6640 (The Pile)

Max Activating Token Index: 852