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

Dataset: The Pile

Neuron 4890 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: 3.5158. Min Range: -3.5158

Max Act: 3.5158. Min Act: -0.0000

Data Index: 144767 (The Pile)

Max Activating Token Index: 118

Text #1

Max Range: 3.5158. Min Range: -3.5158

Max Act: 3.2960. Min Act: -0.0000

Data Index: 879996 (The Pile)

Max Activating Token Index: 192

Text #2

Max Range: 3.5158. Min Range: -3.5158

Max Act: 3.0539. Min Act: -0.0000

Data Index: 1430231 (The Pile)

Max Activating Token Index: 111

Text #3

Max Range: 3.5158. Min Range: -3.5158

Max Act: 3.3749. Min Act: -0.0000

Data Index: 809976 (The Pile)

Max Activating Token Index: 171

Text #4

Max Range: 3.5158. Min Range: -3.5158

Max Act: 2.6873. Min Act: -0.0000

Data Index: 442412 (The Pile)

Max Activating Token Index: 278

Text #5

Max Range: 3.5158. Min Range: -3.5158

Max Act: 3.2859. Min Act: -0.0000

Data Index: 568611 (The Pile)

Max Activating Token Index: 259

Text #6

Max Range: 3.5158. Min Range: -3.5158

Max Act: 2.9508. Min Act: -0.0000

Data Index: 202816 (The Pile)

Max Activating Token Index: 388

Text #7

Max Range: 3.5158. Min Range: -3.5158

Max Act: 3.0952. Min Act: -0.0000

Data Index: 1468005 (The Pile)

Max Activating Token Index: 217

Text #8

Max Range: 3.5158. Min Range: -3.5158

Max Act: 2.8785. Min Act: -0.0000

Data Index: 1857505 (The Pile)

Max Activating Token Index: 85

Text #9

Max Range: 3.5158. Min Range: -3.5158

Max Act: 2.8992. Min Act: -0.0000

Data Index: 1951117 (The Pile)

Max Activating Token Index: 610

Text #10

Max Range: 3.5158. Min Range: -3.5158

Max Act: 2.8235. Min Act: -0.0000

Data Index: 1521560 (The Pile)

Max Activating Token Index: 778

Text #11

Max Range: 3.5158. Min Range: -3.5158

Max Act: 2.6546. Min Act: -0.0000

Data Index: 461386 (The Pile)

Max Activating Token Index: 466

Text #12

Max Range: 3.5158. Min Range: -3.5158

Max Act: 2.5627. Min Act: -0.0000

Data Index: 407905 (The Pile)

Max Activating Token Index: 388

Text #13

Max Range: 3.5158. Min Range: -3.5158

Max Act: 2.8119. Min Act: -0.0000

Data Index: 394858 (The Pile)

Max Activating Token Index: 154

Text #14

Max Range: 3.5158. Min Range: -3.5158

Max Act: 3.1088. Min Act: -0.0000

Data Index: 1317605 (The Pile)

Max Activating Token Index: 251

Text #15

Max Range: 3.5158. Min Range: -3.5158

Max Act: 2.8190. Min Act: -0.0000

Data Index: 907433 (The Pile)

Max Activating Token Index: 415

Text #16

Max Range: 3.5158. Min Range: -3.5158

Max Act: 2.8926. Min Act: -0.0000

Data Index: 1705985 (The Pile)

Max Activating Token Index: 86

Text #17

Max Range: 3.5158. Min Range: -3.5158

Max Act: 2.9218. Min Act: -0.0000

Data Index: 1458691 (The Pile)

Max Activating Token Index: 596

Text #18

Max Range: 3.5158. Min Range: -3.5158

Max Act: 2.5874. Min Act: -0.0000

Data Index: 842429 (The Pile)

Max Activating Token Index: 218

Text #19

Max Range: 3.5158. Min Range: -3.5158

Max Act: 2.4548. Min Act: -0.0000

Data Index: 1652487 (The Pile)

Max Activating Token Index: 392