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

Dataset: The Pile

Neuron 4662 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: 0.6994. Min Range: -0.6994

Max Act: 0.6717. Min Act: -0.0000

Data Index: 468705 (The Pile)

Max Activating Token Index: 897

Text #1

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5952. Min Act: -0.0000

Data Index: 1287770 (The Pile)

Max Activating Token Index: 1003

Text #2

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.6994. Min Act: -0.0000

Data Index: 1985884 (The Pile)

Max Activating Token Index: 585

Text #3

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.6492. Min Act: -0.0000

Data Index: 1508176 (The Pile)

Max Activating Token Index: 142

Text #4

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.6599. Min Act: -0.0000

Data Index: 1318661 (The Pile)

Max Activating Token Index: 844

Text #5

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5921. Min Act: -0.0000

Data Index: 1214679 (The Pile)

Max Activating Token Index: 427

Text #6

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5053. Min Act: -0.0000

Data Index: 1641198 (The Pile)

Max Activating Token Index: 953

Text #7

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5375. Min Act: -0.0000

Data Index: 1360086 (The Pile)

Max Activating Token Index: 294

Text #8

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5934. Min Act: -0.0000

Data Index: 1689030 (The Pile)

Max Activating Token Index: 111

Text #9

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5460. Min Act: -0.0000

Data Index: 1661026 (The Pile)

Max Activating Token Index: 637

Text #10

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5181. Min Act: -0.0000

Data Index: 757977 (The Pile)

Max Activating Token Index: 360

Text #11

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5176. Min Act: -0.0000

Data Index: 1334077 (The Pile)

Max Activating Token Index: 57

Text #12

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4715. Min Act: -0.0000

Data Index: 1870165 (The Pile)

Max Activating Token Index: 901

Text #13

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4568. Min Act: -0.0000

Data Index: 1433930 (The Pile)

Max Activating Token Index: 550

Text #14

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.3806. Min Act: -0.0000

Data Index: 182215 (The Pile)

Max Activating Token Index: 886

Text #15

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4182. Min Act: -0.0000

Data Index: 1901809 (The Pile)

Max Activating Token Index: 38

Text #16

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4193. Min Act: -0.0000

Data Index: 569804 (The Pile)

Max Activating Token Index: 210

Text #17

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.3603. Min Act: -0.0000

Data Index: 28737 (The Pile)

Max Activating Token Index: 140

Text #18

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4061. Min Act: -0.0000

Data Index: 1941167 (The Pile)

Max Activating Token Index: 577

Text #19

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4364. Min Act: -0.0000

Data Index: 1167476 (The Pile)

Max Activating Token Index: 112