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

Dataset: The Pile

Neuron 1802 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.7444. Min Act: -0.0000

Data Index: 1104193 (The Pile)

Max Activating Token Index: 686

Text #1

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.8136. Min Act: -0.0000

Data Index: 1793104 (The Pile)

Max Activating Token Index: 279

Text #2

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.7586. Min Act: -0.0000

Data Index: 113552 (The Pile)

Max Activating Token Index: 47

Text #3

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.7159. Min Act: -0.0000

Data Index: 1886018 (The Pile)

Max Activating Token Index: 238

Text #4

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.7307. Min Act: -0.0000

Data Index: 1274306 (The Pile)

Max Activating Token Index: 69

Text #5

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.7061. Min Act: -0.0000

Data Index: 1017486 (The Pile)

Max Activating Token Index: 248

Text #6

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.6538. Min Act: -0.0000

Data Index: 1770641 (The Pile)

Max Activating Token Index: 453

Text #7

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.5913. Min Act: -0.0000

Data Index: 1689381 (The Pile)

Max Activating Token Index: 207

Text #8

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.6131. Min Act: -0.0000

Data Index: 1059688 (The Pile)

Max Activating Token Index: 591

Text #9

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.6017. Min Act: -0.0000

Data Index: 540128 (The Pile)

Max Activating Token Index: 295

Text #10

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.5809. Min Act: -0.0000

Data Index: 929855 (The Pile)

Max Activating Token Index: 1013

Text #11

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.6221. Min Act: -0.0000

Data Index: 1909612 (The Pile)

Max Activating Token Index: 1022

Text #12

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.5955. Min Act: -0.0000

Data Index: 1621783 (The Pile)

Max Activating Token Index: 949

Text #13

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.5794. Min Act: -0.0000

Data Index: 789679 (The Pile)

Max Activating Token Index: 100

Text #14

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.5567. Min Act: -0.0000

Data Index: 1960235 (The Pile)

Max Activating Token Index: 331

Text #15

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.5967. Min Act: -0.0000

Data Index: 80519 (The Pile)

Max Activating Token Index: 323

Text #16

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.5945. Min Act: -0.0000

Data Index: 1444941 (The Pile)

Max Activating Token Index: 587

Text #17

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.5882. Min Act: -0.0000

Data Index: 630157 (The Pile)

Max Activating Token Index: 540

Text #18

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.6052. Min Act: -0.0000

Data Index: 1321569 (The Pile)

Max Activating Token Index: 285

Text #19

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.5606. Min Act: -0.0000

Data Index: 828251 (The Pile)

Max Activating Token Index: 37