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

Dataset: The Pile

Neuron 3356 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: 0.8670. Min Range: -0.8670

Max Act: 0.8670. Min Act: -0.0000

Data Index: 172409 (The Pile)

Max Activating Token Index: 9

Text #1

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.8116. Min Act: -0.0000

Data Index: 1458003 (The Pile)

Max Activating Token Index: 8

Text #2

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.8116. Min Act: -0.0000

Data Index: 1390903 (The Pile)

Max Activating Token Index: 8

Text #3

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.7863. Min Act: -0.0000

Data Index: 489657 (The Pile)

Max Activating Token Index: 6

Text #4

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.7586. Min Act: -0.0000

Data Index: 1945476 (The Pile)

Max Activating Token Index: 721

Text #5

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6424. Min Act: -0.0000

Data Index: 523983 (The Pile)

Max Activating Token Index: 883

Text #6

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6827. Min Act: -0.0000

Data Index: 1474312 (The Pile)

Max Activating Token Index: 625

Text #7

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.7394. Min Act: -0.0000

Data Index: 1567717 (The Pile)

Max Activating Token Index: 291

Text #8

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.7421. Min Act: -0.0000

Data Index: 881367 (The Pile)

Max Activating Token Index: 159

Text #9

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6751. Min Act: -0.0000

Data Index: 1490249 (The Pile)

Max Activating Token Index: 388

Text #10

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6509. Min Act: -0.0000

Data Index: 713261 (The Pile)

Max Activating Token Index: 449

Text #11

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6384. Min Act: -0.0000

Data Index: 160599 (The Pile)

Max Activating Token Index: 833

Text #12

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6760. Min Act: -0.0000

Data Index: 1552463 (The Pile)

Max Activating Token Index: 404

Text #13

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6133. Min Act: -0.0000

Data Index: 400771 (The Pile)

Max Activating Token Index: 707

Text #14

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6652. Min Act: -0.0000

Data Index: 572615 (The Pile)

Max Activating Token Index: 366

Text #15

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6472. Min Act: -0.0000

Data Index: 465089 (The Pile)

Max Activating Token Index: 353

Text #16

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6459. Min Act: -0.0000

Data Index: 1391361 (The Pile)

Max Activating Token Index: 425

Text #17

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6863. Min Act: -0.0000

Data Index: 276116 (The Pile)

Max Activating Token Index: 622

Text #18

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6405. Min Act: -0.0000

Data Index: 818683 (The Pile)

Max Activating Token Index: 288

Text #19

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6345. Min Act: -0.0000

Data Index: 471408 (The Pile)

Max Activating Token Index: 1004