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

Dataset: The Pile

Neuron 1649 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9444. Min Range: -0.9444

Max Act: 0.9006. Min Act: -0.0000

Data Index: 1289538 (The Pile)

Max Activating Token Index: 835

Text #1

Max Range: 0.9444. Min Range: -0.9444

Max Act: 0.9444. Min Act: -0.0000

Data Index: 696498 (The Pile)

Max Activating Token Index: 493

Text #2

Max Range: 0.9444. Min Range: -0.9444

Max Act: 0.7979. Min Act: -0.0000

Data Index: 687333 (The Pile)

Max Activating Token Index: 728

Text #3

Max Range: 0.9444. Min Range: -0.9444

Max Act: 0.8062. Min Act: -0.0000

Data Index: 1048231 (The Pile)

Max Activating Token Index: 205

Text #4

Max Range: 0.9444. Min Range: -0.9444

Max Act: 0.7417. Min Act: -0.0000

Data Index: 725237 (The Pile)

Max Activating Token Index: 916

Text #5

Max Range: 0.9444. Min Range: -0.9444

Max Act: 0.7694. Min Act: -0.0000

Data Index: 1963789 (The Pile)

Max Activating Token Index: 787

Text #6

Max Range: 0.9444. Min Range: -0.9444

Max Act: 0.7460. Min Act: -0.0000

Data Index: 586239 (The Pile)

Max Activating Token Index: 210

Text #7

Max Range: 0.9444. Min Range: -0.9444

Max Act: 0.7498. Min Act: -0.0000

Data Index: 529579 (The Pile)

Max Activating Token Index: 895

Text #8

Max Range: 0.9444. Min Range: -0.9444

Max Act: 0.6877. Min Act: -0.0000

Data Index: 289428 (The Pile)

Max Activating Token Index: 976

Text #9

Max Range: 0.9444. Min Range: -0.9444

Max Act: 0.6894. Min Act: -0.0000

Data Index: 1222041 (The Pile)

Max Activating Token Index: 838

Text #10

Max Range: 0.9444. Min Range: -0.9444

Max Act: 0.6526. Min Act: -0.0000

Data Index: 1594432 (The Pile)

Max Activating Token Index: 179

Text #11

Max Range: 0.9444. Min Range: -0.9444

Max Act: 0.7095. Min Act: 0.0000

Data Index: 70741 (The Pile)

Max Activating Token Index: 842

Text #12

Max Range: 0.9444. Min Range: -0.9444

Max Act: 0.6385. Min Act: -0.0000

Data Index: 804039 (The Pile)

Max Activating Token Index: 106

Text #13

Max Range: 0.9444. Min Range: -0.9444

Max Act: 0.6326. Min Act: -0.0000

Data Index: 1731435 (The Pile)

Max Activating Token Index: 299

Text #14

Max Range: 0.9444. Min Range: -0.9444

Max Act: 0.6133. Min Act: -0.0000

Data Index: 1170207 (The Pile)

Max Activating Token Index: 284

Text #15

Max Range: 0.9444. Min Range: -0.9444

Max Act: 0.6044. Min Act: -0.0000

Data Index: 1778035 (The Pile)

Max Activating Token Index: 877

Text #16

Max Range: 0.9444. Min Range: -0.9444

Max Act: 0.5584. Min Act: -0.0000

Data Index: 537113 (The Pile)

Max Activating Token Index: 247

Text #17

Max Range: 0.9444. Min Range: -0.9444

Max Act: 0.6051. Min Act: -0.0000

Data Index: 324592 (The Pile)

Max Activating Token Index: 334

Text #18

Max Range: 0.9444. Min Range: -0.9444

Max Act: 0.6004. Min Act: -0.0000

Data Index: 394624 (The Pile)

Max Activating Token Index: 33

Text #19

Max Range: 0.9444. Min Range: -0.9444

Max Act: 0.5323. Min Act: -0.0000

Data Index: 158363 (The Pile)

Max Activating Token Index: 422