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

Dataset: The Pile

Neuron 3068 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: 3.9141. Min Range: -3.9141

Max Act: 3.9141. Min Act: -0.0000

Data Index: 1243620 (The Pile)

Max Activating Token Index: 117

Text #1

Max Range: 3.9141. Min Range: -3.9141

Max Act: 3.6915. Min Act: -0.0000

Data Index: 1953109 (The Pile)

Max Activating Token Index: 6

Text #2

Max Range: 3.9141. Min Range: -3.9141

Max Act: 3.8409. Min Act: -0.0000

Data Index: 1532265 (The Pile)

Max Activating Token Index: 598

Text #3

Max Range: 3.9141. Min Range: -3.9141

Max Act: 3.5812. Min Act: -0.0000

Data Index: 928425 (The Pile)

Max Activating Token Index: 101

Text #4

Max Range: 3.9141. Min Range: -3.9141

Max Act: 3.3878. Min Act: -0.0000

Data Index: 1825089 (The Pile)

Max Activating Token Index: 9

Text #5

Max Range: 3.9141. Min Range: -3.9141

Max Act: 3.5372. Min Act: -0.0000

Data Index: 1991587 (The Pile)

Max Activating Token Index: 239

Text #6

Max Range: 3.9141. Min Range: -3.9141

Max Act: 3.3993. Min Act: -0.0000

Data Index: 377174 (The Pile)

Max Activating Token Index: 830

Text #7

Max Range: 3.9141. Min Range: -3.9141

Max Act: 3.3900. Min Act: -0.0000

Data Index: 1904001 (The Pile)

Max Activating Token Index: 20

Text #8

Max Range: 3.9141. Min Range: -3.9141

Max Act: 3.4112. Min Act: -0.0000

Data Index: 224150 (The Pile)

Max Activating Token Index: 717

Text #9

Max Range: 3.9141. Min Range: -3.9141

Max Act: 3.3730. Min Act: -0.0000

Data Index: 573122 (The Pile)

Max Activating Token Index: 115

Text #10

Max Range: 3.9141. Min Range: -3.9141

Max Act: 3.1765. Min Act: -0.0000

Data Index: 347674 (The Pile)

Max Activating Token Index: 683

Text #11

Max Range: 3.9141. Min Range: -3.9141

Max Act: 3.2475. Min Act: -0.0000

Data Index: 1685212 (The Pile)

Max Activating Token Index: 63

Text #12

Max Range: 3.9141. Min Range: -3.9141

Max Act: 3.3687. Min Act: -0.0000

Data Index: 859102 (The Pile)

Max Activating Token Index: 473

Text #13

Max Range: 3.9141. Min Range: -3.9141

Max Act: 3.3498. Min Act: -0.0000

Data Index: 615397 (The Pile)

Max Activating Token Index: 452

Text #14

Max Range: 3.9141. Min Range: -3.9141

Max Act: 3.2134. Min Act: -0.0000

Data Index: 1224202 (The Pile)

Max Activating Token Index: 161

Text #15

Max Range: 3.9141. Min Range: -3.9141

Max Act: 3.0257. Min Act: -0.0000

Data Index: 1491596 (The Pile)

Max Activating Token Index: 746

Text #16

Max Range: 3.9141. Min Range: -3.9141

Max Act: 2.9829. Min Act: -0.0000

Data Index: 1262835 (The Pile)

Max Activating Token Index: 10

Text #17

Max Range: 3.9141. Min Range: -3.9141

Max Act: 3.1193. Min Act: -0.0000

Data Index: 1395009 (The Pile)

Max Activating Token Index: 226

Text #18

Max Range: 3.9141. Min Range: -3.9141

Max Act: 3.1034. Min Act: -0.0000

Data Index: 924154 (The Pile)

Max Activating Token Index: 717

Text #19

Max Range: 3.9141. Min Range: -3.9141

Max Act: 2.8360. Min Act: -0.0000

Data Index: 762748 (The Pile)

Max Activating Token Index: 637