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

Dataset: The Pile

Neuron 5082 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.5651. Min Range: -7.5651

Max Act: 7.2703. Min Act: -0.0000

Data Index: 1143002 (The Pile)

Max Activating Token Index: 581

Text #1

Max Range: 7.5651. Min Range: -7.5651

Max Act: 6.6635. Min Act: -0.0000

Data Index: 117072 (The Pile)

Max Activating Token Index: 85

Text #2

Max Range: 7.5651. Min Range: -7.5651

Max Act: 7.1898. Min Act: -0.0000

Data Index: 1034782 (The Pile)

Max Activating Token Index: 694

Text #3

Max Range: 7.5651. Min Range: -7.5651

Max Act: 7.5651. Min Act: -0.0000

Data Index: 115448 (The Pile)

Max Activating Token Index: 375

Text #4

Max Range: 7.5651. Min Range: -7.5651

Max Act: 7.3653. Min Act: -0.0000

Data Index: 402217 (The Pile)

Max Activating Token Index: 132

Text #5

Max Range: 7.5651. Min Range: -7.5651

Max Act: 6.6798. Min Act: -0.0000

Data Index: 1050925 (The Pile)

Max Activating Token Index: 216

Text #6

Max Range: 7.5651. Min Range: -7.5651

Max Act: 6.8482. Min Act: -0.0000

Data Index: 1927982 (The Pile)

Max Activating Token Index: 388

Text #7

Max Range: 7.5651. Min Range: -7.5651

Max Act: 6.6351. Min Act: -0.0000

Data Index: 881051 (The Pile)

Max Activating Token Index: 1008

Text #8

Max Range: 7.5651. Min Range: -7.5651

Max Act: 6.8151. Min Act: -0.0000

Data Index: 208989 (The Pile)

Max Activating Token Index: 392

Text #9

Max Range: 7.5651. Min Range: -7.5651

Max Act: 7.1585. Min Act: -0.0000

Data Index: 936523 (The Pile)

Max Activating Token Index: 176

Text #10

Max Range: 7.5651. Min Range: -7.5651

Max Act: 6.5575. Min Act: -0.0000

Data Index: 118286 (The Pile)

Max Activating Token Index: 324

Text #11

Max Range: 7.5651. Min Range: -7.5651

Max Act: 6.5047. Min Act: -0.0000

Data Index: 498919 (The Pile)

Max Activating Token Index: 844

Text #12

Max Range: 7.5651. Min Range: -7.5651

Max Act: 6.5704. Min Act: -0.0000

Data Index: 1945154 (The Pile)

Max Activating Token Index: 109

Text #13

Max Range: 7.5651. Min Range: -7.5651

Max Act: 7.0473. Min Act: -0.0000

Data Index: 883223 (The Pile)

Max Activating Token Index: 778

Text #14

Max Range: 7.5651. Min Range: -7.5651

Max Act: 6.7893. Min Act: -0.0000

Data Index: 338193 (The Pile)

Max Activating Token Index: 357

Text #15

Max Range: 7.5651. Min Range: -7.5651

Max Act: 6.6424. Min Act: -0.0000

Data Index: 1195445 (The Pile)

Max Activating Token Index: 99

Text #16

Max Range: 7.5651. Min Range: -7.5651

Max Act: 6.6655. Min Act: -0.0000

Data Index: 289344 (The Pile)

Max Activating Token Index: 250

Text #17

Max Range: 7.5651. Min Range: -7.5651

Max Act: 6.6771. Min Act: -0.0000

Data Index: 136197 (The Pile)

Max Activating Token Index: 703

Text #18

Max Range: 7.5651. Min Range: -7.5651

Max Act: 6.4687. Min Act: -0.0000

Data Index: 1629200 (The Pile)

Max Activating Token Index: 821

Text #19

Max Range: 7.5651. Min Range: -7.5651

Max Act: 7.1065. Min Act: -0.0000

Data Index: 435284 (The Pile)

Max Activating Token Index: 253