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

Dataset: The Pile

Neuron 1790 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: 1.3808. Min Range: -1.3808

Max Act: 1.3517. Min Act: -0.0000

Data Index: 1871233 (The Pile)

Max Activating Token Index: 199

Text #1

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.3178. Min Act: -0.0000

Data Index: 418532 (The Pile)

Max Activating Token Index: 984

Text #2

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.3808. Min Act: -0.0000

Data Index: 1867566 (The Pile)

Max Activating Token Index: 690

Text #3

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.1984. Min Act: -0.0000

Data Index: 433636 (The Pile)

Max Activating Token Index: 916

Text #4

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.0577. Min Act: -0.0000

Data Index: 366750 (The Pile)

Max Activating Token Index: 26

Text #5

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.0673. Min Act: -0.0000

Data Index: 965342 (The Pile)

Max Activating Token Index: 983

Text #6

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.0111. Min Act: -0.0000

Data Index: 174093 (The Pile)

Max Activating Token Index: 96

Text #7

Max Range: 1.3808. Min Range: -1.3808

Max Act: 0.9945. Min Act: -0.0000

Data Index: 1594328 (The Pile)

Max Activating Token Index: 65

Text #8

Max Range: 1.3808. Min Range: -1.3808

Max Act: 0.8750. Min Act: -0.0000

Data Index: 1073708 (The Pile)

Max Activating Token Index: 1007

Text #9

Max Range: 1.3808. Min Range: -1.3808

Max Act: 0.9069. Min Act: -0.0000

Data Index: 248728 (The Pile)

Max Activating Token Index: 792

Text #10

Max Range: 1.3808. Min Range: -1.3808

Max Act: 0.9480. Min Act: -0.0000

Data Index: 869167 (The Pile)

Max Activating Token Index: 816

Text #11

Max Range: 1.3808. Min Range: -1.3808

Max Act: 0.8856. Min Act: -0.0000

Data Index: 1867755 (The Pile)

Max Activating Token Index: 602

Text #12

Max Range: 1.3808. Min Range: -1.3808

Max Act: 0.9746. Min Act: -0.0000

Data Index: 279944 (The Pile)

Max Activating Token Index: 712

Text #13

Max Range: 1.3808. Min Range: -1.3808

Max Act: 0.9836. Min Act: -0.0000

Data Index: 83231 (The Pile)

Max Activating Token Index: 63

Text #14

Max Range: 1.3808. Min Range: -1.3808

Max Act: 0.9161. Min Act: -0.0000

Data Index: 31304 (The Pile)

Max Activating Token Index: 309

Text #15

Max Range: 1.3808. Min Range: -1.3808

Max Act: 0.9336. Min Act: -0.0000

Data Index: 54811 (The Pile)

Max Activating Token Index: 252

Text #16

Max Range: 1.3808. Min Range: -1.3808

Max Act: 0.9408. Min Act: -0.0000

Data Index: 1515062 (The Pile)

Max Activating Token Index: 546

Text #17

Max Range: 1.3808. Min Range: -1.3808

Max Act: 0.8737. Min Act: -0.0000

Data Index: 95626 (The Pile)

Max Activating Token Index: 90

Text #18

Max Range: 1.3808. Min Range: -1.3808

Max Act: 0.8717. Min Act: -0.0000

Data Index: 620147 (The Pile)

Max Activating Token Index: 117

Text #19

Max Range: 1.3808. Min Range: -1.3808

Max Act: 0.9145. Min Act: -0.0000

Data Index: 1510073 (The Pile)

Max Activating Token Index: 248