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

Dataset: The Pile

Neuron 1058 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7930. Min Range: -5.7930

Max Act: 5.7930. Min Act: -0.0000

Data Index: 1547097 (The Pile)

Max Activating Token Index: 862

Text #1

Max Range: 5.7930. Min Range: -5.7930

Max Act: 5.6075. Min Act: -0.0000

Data Index: 591423 (The Pile)

Max Activating Token Index: 572

Text #2

Max Range: 5.7930. Min Range: -5.7930

Max Act: 5.4174. Min Act: -0.0000

Data Index: 325229 (The Pile)

Max Activating Token Index: 343

Text #3

Max Range: 5.7930. Min Range: -5.7930

Max Act: 5.6792. Min Act: -0.0000

Data Index: 1257940 (The Pile)

Max Activating Token Index: 835

Text #4

Max Range: 5.7930. Min Range: -5.7930

Max Act: 5.4317. Min Act: -0.0000

Data Index: 1388207 (The Pile)

Max Activating Token Index: 962

Text #5

Max Range: 5.7930. Min Range: -5.7930

Max Act: 4.7286. Min Act: -0.0000

Data Index: 1083790 (The Pile)

Max Activating Token Index: 214

Text #6

Max Range: 5.7930. Min Range: -5.7930

Max Act: 4.5581. Min Act: -0.0000

Data Index: 391548 (The Pile)

Max Activating Token Index: 500

Text #7

Max Range: 5.7930. Min Range: -5.7930

Max Act: 4.1765. Min Act: -0.0000

Data Index: 991012 (The Pile)

Max Activating Token Index: 189

Text #8

Max Range: 5.7930. Min Range: -5.7930

Max Act: 4.1645. Min Act: -0.0000

Data Index: 1358915 (The Pile)

Max Activating Token Index: 133

Text #9

Max Range: 5.7930. Min Range: -5.7930

Max Act: 3.8958. Min Act: -0.0000

Data Index: 978721 (The Pile)

Max Activating Token Index: 578

Text #10

Max Range: 5.7930. Min Range: -5.7930

Max Act: 3.8887. Min Act: -0.0000

Data Index: 568788 (The Pile)

Max Activating Token Index: 960

Text #11

Max Range: 5.7930. Min Range: -5.7930

Max Act: 3.3492. Min Act: -0.0000

Data Index: 975959 (The Pile)

Max Activating Token Index: 911

Text #12

Max Range: 5.7930. Min Range: -5.7930

Max Act: 3.6278. Min Act: -0.0000

Data Index: 917334 (The Pile)

Max Activating Token Index: 800

Text #13

Max Range: 5.7930. Min Range: -5.7930

Max Act: 3.6099. Min Act: -0.0000

Data Index: 912211 (The Pile)

Max Activating Token Index: 591

Text #14

Max Range: 5.7930. Min Range: -5.7930

Max Act: 3.6209. Min Act: -0.0000

Data Index: 610730 (The Pile)

Max Activating Token Index: 644

Text #15

Max Range: 5.7930. Min Range: -5.7930

Max Act: 3.3205. Min Act: -0.0000

Data Index: 733700 (The Pile)

Max Activating Token Index: 241

Text #16

Max Range: 5.7930. Min Range: -5.7930

Max Act: 3.6003. Min Act: -0.0000

Data Index: 1830930 (The Pile)

Max Activating Token Index: 530

Text #17

Max Range: 5.7930. Min Range: -5.7930

Max Act: 3.1611. Min Act: -0.0000

Data Index: 1354199 (The Pile)

Max Activating Token Index: 650

Text #18

Max Range: 5.7930. Min Range: -5.7930

Max Act: 3.6553. Min Act: -0.0000

Data Index: 602038 (The Pile)

Max Activating Token Index: 295

Text #19

Max Range: 5.7930. Min Range: -5.7930

Max Act: 3.4532. Min Act: -0.0000

Data Index: 860208 (The Pile)

Max Activating Token Index: 884