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

Dataset: The Pile

Neuron 1232 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: 3.8013. Min Range: -3.8013

Max Act: 3.8013. Min Act: -0.0000

Data Index: 1433174 (The Pile)

Max Activating Token Index: 846

Text #1

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.7355. Min Act: -0.0000

Data Index: 504061 (The Pile)

Max Activating Token Index: 874

Text #2

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.6755. Min Act: -0.0000

Data Index: 139123 (The Pile)

Max Activating Token Index: 288

Text #3

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.6835. Min Act: -0.0000

Data Index: 237629 (The Pile)

Max Activating Token Index: 925

Text #4

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.6418. Min Act: -0.0000

Data Index: 974559 (The Pile)

Max Activating Token Index: 330

Text #5

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.7520. Min Act: -0.0000

Data Index: 930577 (The Pile)

Max Activating Token Index: 698

Text #6

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.3589. Min Act: -0.0000

Data Index: 714828 (The Pile)

Max Activating Token Index: 322

Text #7

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.4547. Min Act: -0.0000

Data Index: 1117076 (The Pile)

Max Activating Token Index: 958

Text #8

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.4252. Min Act: -0.0000

Data Index: 1797437 (The Pile)

Max Activating Token Index: 593

Text #9

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.4559. Min Act: -0.0000

Data Index: 1785368 (The Pile)

Max Activating Token Index: 804

Text #10

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.5469. Min Act: -0.0000

Data Index: 277873 (The Pile)

Max Activating Token Index: 711

Text #11

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.5584. Min Act: -0.0000

Data Index: 1701966 (The Pile)

Max Activating Token Index: 575

Text #12

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.2115. Min Act: -0.0000

Data Index: 1440640 (The Pile)

Max Activating Token Index: 557

Text #13

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.3579. Min Act: -0.0000

Data Index: 390481 (The Pile)

Max Activating Token Index: 265

Text #14

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.1766. Min Act: -0.0000

Data Index: 118205 (The Pile)

Max Activating Token Index: 319

Text #15

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.3316. Min Act: -0.0000

Data Index: 1041385 (The Pile)

Max Activating Token Index: 415

Text #16

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.2565. Min Act: -0.0000

Data Index: 559932 (The Pile)

Max Activating Token Index: 183

Text #17

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.1123. Min Act: -0.0000

Data Index: 786438 (The Pile)

Max Activating Token Index: 296

Text #18

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.0885. Min Act: -0.0000

Data Index: 760578 (The Pile)

Max Activating Token Index: 53

Text #19

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.2297. Min Act: -0.0000

Data Index: 1152900 (The Pile)

Max Activating Token Index: 790