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

Dataset: The Pile

Neuron 624 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: 0.2800. Min Range: -0.2800

Max Act: 0.2794. Min Act: -0.0000

Data Index: 1356441 (The Pile)

Max Activating Token Index: 442

Text #1

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2800. Min Act: -0.0000

Data Index: 691624 (The Pile)

Max Activating Token Index: 419

Text #2

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2654. Min Act: -0.0000

Data Index: 1357356 (The Pile)

Max Activating Token Index: 925

Text #3

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2564. Min Act: -0.0000

Data Index: 1634382 (The Pile)

Max Activating Token Index: 148

Text #4

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2446. Min Act: -0.0000

Data Index: 552251 (The Pile)

Max Activating Token Index: 535

Text #5

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2624. Min Act: -0.0000

Data Index: 1886054 (The Pile)

Max Activating Token Index: 40

Text #6

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2587. Min Act: -0.0000

Data Index: 1701533 (The Pile)

Max Activating Token Index: 281

Text #7

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2402. Min Act: -0.0000

Data Index: 1404091 (The Pile)

Max Activating Token Index: 23

Text #8

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2642. Min Act: -0.0000

Data Index: 1766244 (The Pile)

Max Activating Token Index: 687

Text #9

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2361. Min Act: -0.0000

Data Index: 330630 (The Pile)

Max Activating Token Index: 228

Text #10

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2346. Min Act: -0.0000

Data Index: 29465 (The Pile)

Max Activating Token Index: 944

Text #11

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2262. Min Act: -0.0000

Data Index: 186326 (The Pile)

Max Activating Token Index: 884

Text #12

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2137. Min Act: -0.0000

Data Index: 1295742 (The Pile)

Max Activating Token Index: 19

Text #13

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2138. Min Act: -0.0000

Data Index: 1995925 (The Pile)

Max Activating Token Index: 52

Text #14

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2090. Min Act: -0.0000

Data Index: 1439661 (The Pile)

Max Activating Token Index: 449

Text #15

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2071. Min Act: -0.0000

Data Index: 33456 (The Pile)

Max Activating Token Index: 317

Text #16

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2230. Min Act: -0.0000

Data Index: 76242 (The Pile)

Max Activating Token Index: 113

Text #17

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2077. Min Act: -0.0000

Data Index: 195887 (The Pile)

Max Activating Token Index: 616

Text #18

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2156. Min Act: -0.0000

Data Index: 713240 (The Pile)

Max Activating Token Index: 186

Text #19

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2006. Min Act: -0.0000

Data Index: 1371255 (The Pile)

Max Activating Token Index: 178