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

Dataset: The Pile

Neuron 713 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: 0.7958. Min Range: -0.7958

Max Act: 0.7958. Min Act: -0.0000

Data Index: 997375 (The Pile)

Max Activating Token Index: 624

Text #1

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.6953. Min Act: -0.0000

Data Index: 151937 (The Pile)

Max Activating Token Index: 275

Text #2

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.6966. Min Act: -0.0000

Data Index: 759969 (The Pile)

Max Activating Token Index: 950

Text #3

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.7011. Min Act: -0.0000

Data Index: 172093 (The Pile)

Max Activating Token Index: 309

Text #4

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.6954. Min Act: -0.0000

Data Index: 437290 (The Pile)

Max Activating Token Index: 275

Text #5

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.6376. Min Act: -0.0000

Data Index: 1098373 (The Pile)

Max Activating Token Index: 446

Text #6

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.6263. Min Act: -0.0000

Data Index: 1847519 (The Pile)

Max Activating Token Index: 873

Text #7

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.6045. Min Act: -0.0000

Data Index: 428830 (The Pile)

Max Activating Token Index: 907

Text #8

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.5599. Min Act: -0.0000

Data Index: 1097053 (The Pile)

Max Activating Token Index: 825

Text #9

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.5981. Min Act: -0.0000

Data Index: 242062 (The Pile)

Max Activating Token Index: 522

Text #10

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.6301. Min Act: -0.0000

Data Index: 1423140 (The Pile)

Max Activating Token Index: 690

Text #11

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.5895. Min Act: -0.0000

Data Index: 1000435 (The Pile)

Max Activating Token Index: 709

Text #12

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.5865. Min Act: -0.0000

Data Index: 1063642 (The Pile)

Max Activating Token Index: 457

Text #13

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.6031. Min Act: -0.0000

Data Index: 1163364 (The Pile)

Max Activating Token Index: 29

Text #14

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.6033. Min Act: -0.0000

Data Index: 1242375 (The Pile)

Max Activating Token Index: 354

Text #15

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.6018. Min Act: -0.0000

Data Index: 1896214 (The Pile)

Max Activating Token Index: 941

Text #16

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.5836. Min Act: -0.0000

Data Index: 1986912 (The Pile)

Max Activating Token Index: 450

Text #17

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.6007. Min Act: -0.0000

Data Index: 1481499 (The Pile)

Max Activating Token Index: 159

Text #18

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.6033. Min Act: -0.0000

Data Index: 80233 (The Pile)

Max Activating Token Index: 233

Text #19

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.5987. Min Act: -0.0000

Data Index: 1996062 (The Pile)

Max Activating Token Index: 355