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

Dataset: The Pile

Neuron 2067 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: 0.5257. Min Range: -0.5257

Max Act: 0.5068. Min Act: -0.0000

Data Index: 377977 (The Pile)

Max Activating Token Index: 880

Text #1

Max Range: 0.5257. Min Range: -0.5257

Max Act: 0.4908. Min Act: -0.0000

Data Index: 855874 (The Pile)

Max Activating Token Index: 701

Text #2

Max Range: 0.5257. Min Range: -0.5257

Max Act: 0.4724. Min Act: -0.0000

Data Index: 756454 (The Pile)

Max Activating Token Index: 876

Text #3

Max Range: 0.5257. Min Range: -0.5257

Max Act: 0.5257. Min Act: -0.0000

Data Index: 1428799 (The Pile)

Max Activating Token Index: 595

Text #4

Max Range: 0.5257. Min Range: -0.5257

Max Act: 0.5143. Min Act: -0.0000

Data Index: 1703078 (The Pile)

Max Activating Token Index: 594

Text #5

Max Range: 0.5257. Min Range: -0.5257

Max Act: 0.4901. Min Act: -0.0000

Data Index: 426748 (The Pile)

Max Activating Token Index: 176

Text #6

Max Range: 0.5257. Min Range: -0.5257

Max Act: 0.4647. Min Act: -0.0000

Data Index: 1008794 (The Pile)

Max Activating Token Index: 422

Text #7

Max Range: 0.5257. Min Range: -0.5257

Max Act: 0.4767. Min Act: -0.0000

Data Index: 1762786 (The Pile)

Max Activating Token Index: 971

Text #8

Max Range: 0.5257. Min Range: -0.5257

Max Act: 0.4602. Min Act: -0.0000

Data Index: 1001749 (The Pile)

Max Activating Token Index: 531

Text #9

Max Range: 0.5257. Min Range: -0.5257

Max Act: 0.4653. Min Act: -0.0000

Data Index: 779023 (The Pile)

Max Activating Token Index: 713

Text #10

Max Range: 0.5257. Min Range: -0.5257

Max Act: 0.4679. Min Act: -0.0000

Data Index: 134064 (The Pile)

Max Activating Token Index: 118

Text #11

Max Range: 0.5257. Min Range: -0.5257

Max Act: 0.4368. Min Act: -0.0000

Data Index: 391991 (The Pile)

Max Activating Token Index: 176

Text #12

Max Range: 0.5257. Min Range: -0.5257

Max Act: 0.4206. Min Act: -0.0000

Data Index: 1934433 (The Pile)

Max Activating Token Index: 201

Text #13

Max Range: 0.5257. Min Range: -0.5257

Max Act: 0.4607. Min Act: -0.0000

Data Index: 1969781 (The Pile)

Max Activating Token Index: 476

Text #14

Max Range: 0.5257. Min Range: -0.5257

Max Act: 0.4468. Min Act: -0.0000

Data Index: 942578 (The Pile)

Max Activating Token Index: 955

Text #15

Max Range: 0.5257. Min Range: -0.5257

Max Act: 0.4642. Min Act: -0.0000

Data Index: 908372 (The Pile)

Max Activating Token Index: 538

Text #16

Max Range: 0.5257. Min Range: -0.5257

Max Act: 0.4408. Min Act: -0.0000

Data Index: 1525074 (The Pile)

Max Activating Token Index: 431

Text #17

Max Range: 0.5257. Min Range: -0.5257

Max Act: 0.4519. Min Act: -0.0000

Data Index: 162496 (The Pile)

Max Activating Token Index: 517

Text #18

Max Range: 0.5257. Min Range: -0.5257

Max Act: 0.4255. Min Act: -0.0000

Data Index: 311403 (The Pile)

Max Activating Token Index: 856

Text #19

Max Range: 0.5257. Min Range: -0.5257

Max Act: 0.4550. Min Act: -0.0000

Data Index: 1296824 (The Pile)

Max Activating Token Index: 458