Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 190 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.8139. Min Act: -0.0000

Data Index: 1303513 (The Pile)

Max Activating Token Index: 545

Text #1

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.5665. Min Act: -0.0000

Data Index: 658996 (The Pile)

Max Activating Token Index: 973

Text #2

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.5585. Min Act: -0.0000

Data Index: 445004 (The Pile)

Max Activating Token Index: 472

Text #3

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.5517. Min Act: -0.0000

Data Index: 148986 (The Pile)

Max Activating Token Index: 192

Text #4

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.5319. Min Act: -0.0000

Data Index: 1431837 (The Pile)

Max Activating Token Index: 276

Text #5

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.4990. Min Act: -0.0000

Data Index: 776905 (The Pile)

Max Activating Token Index: 654

Text #6

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.5082. Min Act: -0.0000

Data Index: 435692 (The Pile)

Max Activating Token Index: 225

Text #7

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.5080. Min Act: -0.0000

Data Index: 1914461 (The Pile)

Max Activating Token Index: 885

Text #8

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.4702. Min Act: -0.0000

Data Index: 577920 (The Pile)

Max Activating Token Index: 675

Text #9

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.4958. Min Act: -0.0000

Data Index: 1316861 (The Pile)

Max Activating Token Index: 424

Text #10

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.4879. Min Act: -0.0000

Data Index: 751691 (The Pile)

Max Activating Token Index: 499

Text #11

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.4574. Min Act: -0.0000

Data Index: 680872 (The Pile)

Max Activating Token Index: 863

Text #12

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.4219. Min Act: -0.0000

Data Index: 1206787 (The Pile)

Max Activating Token Index: 283

Text #13

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.4655. Min Act: -0.0000

Data Index: 957999 (The Pile)

Max Activating Token Index: 129

Text #14

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.4620. Min Act: -0.0000

Data Index: 1179424 (The Pile)

Max Activating Token Index: 189

Text #15

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.4000. Min Act: -0.0000

Data Index: 1551198 (The Pile)

Max Activating Token Index: 798

Text #16

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.4425. Min Act: -0.0000

Data Index: 1220511 (The Pile)

Max Activating Token Index: 222

Text #17

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.4298. Min Act: -0.0000

Data Index: 204412 (The Pile)

Max Activating Token Index: 376

Text #18

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.4312. Min Act: -0.0000

Data Index: 252648 (The Pile)

Max Activating Token Index: 718

Text #19

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.4860. Min Act: -0.0000

Data Index: 73538 (The Pile)

Max Activating Token Index: 1020