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

Dataset: The Pile

Neuron 1431 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: 0.8438. Min Range: -0.8438

Max Act: 0.8438. Min Act: -0.0000

Data Index: 370081 (The Pile)

Max Activating Token Index: 184

Text #1

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.7816. Min Act: -0.0000

Data Index: 317413 (The Pile)

Max Activating Token Index: 859

Text #2

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.7903. Min Act: -0.0000

Data Index: 559991 (The Pile)

Max Activating Token Index: 492

Text #3

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6098. Min Act: -0.0000

Data Index: 1617048 (The Pile)

Max Activating Token Index: 805

Text #4

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6989. Min Act: -0.0000

Data Index: 1335152 (The Pile)

Max Activating Token Index: 621

Text #5

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.8386. Min Act: -0.0000

Data Index: 1973462 (The Pile)

Max Activating Token Index: 895

Text #6

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6973. Min Act: -0.0000

Data Index: 737435 (The Pile)

Max Activating Token Index: 295

Text #7

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6278. Min Act: -0.0000

Data Index: 816982 (The Pile)

Max Activating Token Index: 500

Text #8

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6943. Min Act: -0.0000

Data Index: 367264 (The Pile)

Max Activating Token Index: 125

Text #9

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.7219. Min Act: -0.0000

Data Index: 1584798 (The Pile)

Max Activating Token Index: 146

Text #10

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6895. Min Act: -0.0000

Data Index: 226831 (The Pile)

Max Activating Token Index: 603

Text #11

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6557. Min Act: -0.0000

Data Index: 1841019 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6769. Min Act: -0.0000

Data Index: 1950922 (The Pile)

Max Activating Token Index: 38

Text #13

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6943. Min Act: -0.0000

Data Index: 284796 (The Pile)

Max Activating Token Index: 246

Text #14

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6675. Min Act: -0.0000

Data Index: 1927188 (The Pile)

Max Activating Token Index: 191

Text #15

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6459. Min Act: -0.0000

Data Index: 1643283 (The Pile)

Max Activating Token Index: 188

Text #16

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6623. Min Act: -0.0000

Data Index: 181312 (The Pile)

Max Activating Token Index: 28

Text #17

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6832. Min Act: -0.0000

Data Index: 1603925 (The Pile)

Max Activating Token Index: 633

Text #18

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6513. Min Act: -0.0000

Data Index: 1924301 (The Pile)

Max Activating Token Index: 191

Text #19

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6164. Min Act: -0.0000

Data Index: 1463853 (The Pile)

Max Activating Token Index: 150