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

Dataset: The Pile

Neuron 4247 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: 1.0876. Min Range: -1.0876

Max Act: 1.0876. Min Act: -0.0000

Data Index: 983837 (The Pile)

Max Activating Token Index: 221

Text #1

Max Range: 1.0876. Min Range: -1.0876

Max Act: 0.9908. Min Act: -0.0000

Data Index: 303362 (The Pile)

Max Activating Token Index: 653

Text #2

Max Range: 1.0876. Min Range: -1.0876

Max Act: 0.9437. Min Act: -0.0000

Data Index: 31004 (The Pile)

Max Activating Token Index: 281

Text #3

Max Range: 1.0876. Min Range: -1.0876

Max Act: 0.9609. Min Act: -0.0000

Data Index: 582147 (The Pile)

Max Activating Token Index: 945

Text #4

Max Range: 1.0876. Min Range: -1.0876

Max Act: 0.7226. Min Act: -0.0000

Data Index: 1062703 (The Pile)

Max Activating Token Index: 384

Text #5

Max Range: 1.0876. Min Range: -1.0876

Max Act: 0.7952. Min Act: -0.0000

Data Index: 963731 (The Pile)

Max Activating Token Index: 690

Text #6

Max Range: 1.0876. Min Range: -1.0876

Max Act: 0.6518. Min Act: -0.0000

Data Index: 1863340 (The Pile)

Max Activating Token Index: 232

Text #7

Max Range: 1.0876. Min Range: -1.0876

Max Act: 0.6491. Min Act: -0.0000

Data Index: 1760409 (The Pile)

Max Activating Token Index: 289

Text #8

Max Range: 1.0876. Min Range: -1.0876

Max Act: 0.6652. Min Act: -0.0000

Data Index: 381392 (The Pile)

Max Activating Token Index: 253

Text #9

Max Range: 1.0876. Min Range: -1.0876

Max Act: 0.5697. Min Act: -0.0000

Data Index: 742220 (The Pile)

Max Activating Token Index: 970

Text #10

Max Range: 1.0876. Min Range: -1.0876

Max Act: 0.5502. Min Act: -0.0000

Data Index: 1925234 (The Pile)

Max Activating Token Index: 192

Text #11

Max Range: 1.0876. Min Range: -1.0876

Max Act: 0.6377. Min Act: -0.0000

Data Index: 1239246 (The Pile)

Max Activating Token Index: 699

Text #12

Max Range: 1.0876. Min Range: -1.0876

Max Act: 0.5870. Min Act: -0.0000

Data Index: 571581 (The Pile)

Max Activating Token Index: 677

Text #13

Max Range: 1.0876. Min Range: -1.0876

Max Act: 0.6145. Min Act: -0.0000

Data Index: 1448862 (The Pile)

Max Activating Token Index: 584

Text #14

Max Range: 1.0876. Min Range: -1.0876

Max Act: 0.5793. Min Act: -0.0000

Data Index: 390145 (The Pile)

Max Activating Token Index: 115

Text #15

Max Range: 1.0876. Min Range: -1.0876

Max Act: 0.5557. Min Act: -0.0000

Data Index: 350409 (The Pile)

Max Activating Token Index: 113

Text #16

Max Range: 1.0876. Min Range: -1.0876

Max Act: 0.5463. Min Act: -0.0000

Data Index: 1793563 (The Pile)

Max Activating Token Index: 913

Text #17

Max Range: 1.0876. Min Range: -1.0876

Max Act: 0.5379. Min Act: -0.0000

Data Index: 1614906 (The Pile)

Max Activating Token Index: 484

Text #18

Max Range: 1.0876. Min Range: -1.0876

Max Act: 0.5084. Min Act: -0.0000

Data Index: 1315159 (The Pile)

Max Activating Token Index: 613

Text #19

Max Range: 1.0876. Min Range: -1.0876

Max Act: 0.5485. Min Act: -0.0000

Data Index: 1600743 (The Pile)

Max Activating Token Index: 488