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

Dataset: The Pile

Neuron 691 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: 0.8012. Min Range: -0.8012

Max Act: 0.6368. Min Act: -0.0000

Data Index: 1210773 (The Pile)

Max Activating Token Index: 525

Text #1

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.7069. Min Act: -0.0000

Data Index: 321800 (The Pile)

Max Activating Token Index: 869

Text #2

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6730. Min Act: -0.0000

Data Index: 1522739 (The Pile)

Max Activating Token Index: 172

Text #3

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.8012. Min Act: -0.0000

Data Index: 1087022 (The Pile)

Max Activating Token Index: 497

Text #4

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6617. Min Act: -0.0000

Data Index: 1300893 (The Pile)

Max Activating Token Index: 416

Text #5

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6450. Min Act: -0.0000

Data Index: 1888980 (The Pile)

Max Activating Token Index: 922

Text #6

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6380. Min Act: -0.0000

Data Index: 144440 (The Pile)

Max Activating Token Index: 265

Text #7

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.5888. Min Act: -0.0000

Data Index: 1550847 (The Pile)

Max Activating Token Index: 222

Text #8

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6531. Min Act: -0.0000

Data Index: 1214721 (The Pile)

Max Activating Token Index: 769

Text #9

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.5642. Min Act: -0.0000

Data Index: 674012 (The Pile)

Max Activating Token Index: 405

Text #10

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.5575. Min Act: -0.0000

Data Index: 741062 (The Pile)

Max Activating Token Index: 616

Text #11

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.5560. Min Act: -0.0000

Data Index: 1191566 (The Pile)

Max Activating Token Index: 698

Text #12

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6319. Min Act: -0.0000

Data Index: 1984423 (The Pile)

Max Activating Token Index: 18

Text #13

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.5726. Min Act: -0.0000

Data Index: 44456 (The Pile)

Max Activating Token Index: 650

Text #14

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.5458. Min Act: -0.0000

Data Index: 1377497 (The Pile)

Max Activating Token Index: 54

Text #15

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.5754. Min Act: -0.0000

Data Index: 219578 (The Pile)

Max Activating Token Index: 87

Text #16

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.5063. Min Act: -0.0000

Data Index: 1628835 (The Pile)

Max Activating Token Index: 276

Text #17

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.5209. Min Act: -0.0000

Data Index: 512604 (The Pile)

Max Activating Token Index: 701

Text #18

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.5552. Min Act: -0.0000

Data Index: 1563261 (The Pile)

Max Activating Token Index: 178

Text #19

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.5693. Min Act: -0.0000

Data Index: 1906487 (The Pile)

Max Activating Token Index: 105