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

Dataset: The Pile

Neuron 4570 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.3191. Min Act: -0.0000

Data Index: 698481 (The Pile)

Max Activating Token Index: 660

Text #1

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.2872. Min Act: -0.0000

Data Index: 923512 (The Pile)

Max Activating Token Index: 90

Text #2

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.4163. Min Act: -0.0000

Data Index: 1721026 (The Pile)

Max Activating Token Index: 426

Text #3

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.1994. Min Act: -0.0000

Data Index: 1499080 (The Pile)

Max Activating Token Index: 786

Text #4

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.1058. Min Act: -0.0001

Data Index: 306791 (The Pile)

Max Activating Token Index: 442

Text #5

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.1597. Min Act: -0.0000

Data Index: 234900 (The Pile)

Max Activating Token Index: 821

Text #6

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.2761. Min Act: -0.0001

Data Index: 13531 (The Pile)

Max Activating Token Index: 63

Text #7

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.0898. Min Act: -0.0000

Data Index: 1614034 (The Pile)

Max Activating Token Index: 560

Text #8

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.0872. Min Act: -0.0000

Data Index: 1034170 (The Pile)

Max Activating Token Index: 11

Text #9

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.0512. Min Act: -0.0000

Data Index: 820321 (The Pile)

Max Activating Token Index: 284

Text #10

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.0532. Min Act: -0.0000

Data Index: 613528 (The Pile)

Max Activating Token Index: 894

Text #11

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.0099. Min Act: -0.0000

Data Index: 1011836 (The Pile)

Max Activating Token Index: 158

Text #12

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.0566. Min Act: -0.0000

Data Index: 1526848 (The Pile)

Max Activating Token Index: 740

Text #13

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.0590. Min Act: -0.0000

Data Index: 1870644 (The Pile)

Max Activating Token Index: 707

Text #14

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.0256. Min Act: -0.0000

Data Index: 1050992 (The Pile)

Max Activating Token Index: 501

Text #15

Max Range: 1.4163. Min Range: -1.4163

Max Act: 0.9798. Min Act: -0.0000

Data Index: 822734 (The Pile)

Max Activating Token Index: 267

Text #16

Max Range: 1.4163. Min Range: -1.4163

Max Act: 0.9745. Min Act: -0.0000

Data Index: 443962 (The Pile)

Max Activating Token Index: 96

Text #17

Max Range: 1.4163. Min Range: -1.4163

Max Act: 0.9691. Min Act: -0.0001

Data Index: 1086856 (The Pile)

Max Activating Token Index: 153

Text #18

Max Range: 1.4163. Min Range: -1.4163

Max Act: 0.9393. Min Act: -0.0001

Data Index: 1535930 (The Pile)

Max Activating Token Index: 262

Text #19

Max Range: 1.4163. Min Range: -1.4163

Max Act: 0.9623. Min Act: -0.0000

Data Index: 88017 (The Pile)

Max Activating Token Index: 499