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

Dataset: The Pile

Neuron 4140 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: 1.5447. Min Range: -1.5447

Max Act: 1.4075. Min Act: -0.0000

Data Index: 1597536 (The Pile)

Max Activating Token Index: 622

Text #1

Max Range: 1.5447. Min Range: -1.5447

Max Act: 1.5447. Min Act: -0.0000

Data Index: 1469573 (The Pile)

Max Activating Token Index: 746

Text #2

Max Range: 1.5447. Min Range: -1.5447

Max Act: 1.2893. Min Act: -0.0000

Data Index: 206822 (The Pile)

Max Activating Token Index: 905

Text #3

Max Range: 1.5447. Min Range: -1.5447

Max Act: 1.2944. Min Act: -0.0000

Data Index: 1197557 (The Pile)

Max Activating Token Index: 408

Text #4

Max Range: 1.5447. Min Range: -1.5447

Max Act: 1.1393. Min Act: -0.0000

Data Index: 374073 (The Pile)

Max Activating Token Index: 174

Text #5

Max Range: 1.5447. Min Range: -1.5447

Max Act: 0.9982. Min Act: -0.0000

Data Index: 1899672 (The Pile)

Max Activating Token Index: 312

Text #6

Max Range: 1.5447. Min Range: -1.5447

Max Act: 0.9862. Min Act: -0.0000

Data Index: 207603 (The Pile)

Max Activating Token Index: 560

Text #7

Max Range: 1.5447. Min Range: -1.5447

Max Act: 0.9449. Min Act: -0.0000

Data Index: 1827554 (The Pile)

Max Activating Token Index: 615

Text #8

Max Range: 1.5447. Min Range: -1.5447

Max Act: 0.9276. Min Act: -0.0000

Data Index: 1328741 (The Pile)

Max Activating Token Index: 972

Text #9

Max Range: 1.5447. Min Range: -1.5447

Max Act: 0.9374. Min Act: -0.0000

Data Index: 1238296 (The Pile)

Max Activating Token Index: 653

Text #10

Max Range: 1.5447. Min Range: -1.5447

Max Act: 0.8807. Min Act: -0.0000

Data Index: 1808270 (The Pile)

Max Activating Token Index: 361

Text #11

Max Range: 1.5447. Min Range: -1.5447

Max Act: 0.8479. Min Act: -0.0000

Data Index: 382050 (The Pile)

Max Activating Token Index: 933

Text #12

Max Range: 1.5447. Min Range: -1.5447

Max Act: 0.8420. Min Act: -0.0000

Data Index: 810624 (The Pile)

Max Activating Token Index: 703

Text #13

Max Range: 1.5447. Min Range: -1.5447

Max Act: 0.8553. Min Act: -0.0000

Data Index: 397468 (The Pile)

Max Activating Token Index: 410

Text #14

Max Range: 1.5447. Min Range: -1.5447

Max Act: 0.8221. Min Act: -0.0000

Data Index: 1816744 (The Pile)

Max Activating Token Index: 910

Text #15

Max Range: 1.5447. Min Range: -1.5447

Max Act: 0.7998. Min Act: -0.0000

Data Index: 19410 (The Pile)

Max Activating Token Index: 407

Text #16

Max Range: 1.5447. Min Range: -1.5447

Max Act: 0.7316. Min Act: -0.0000

Data Index: 558630 (The Pile)

Max Activating Token Index: 383

Text #17

Max Range: 1.5447. Min Range: -1.5447

Max Act: 0.7142. Min Act: -0.0000

Data Index: 1939679 (The Pile)

Max Activating Token Index: 686

Text #18

Max Range: 1.5447. Min Range: -1.5447

Max Act: 0.7024. Min Act: -0.0000

Data Index: 730959 (The Pile)

Max Activating Token Index: 983

Text #19

Max Range: 1.5447. Min Range: -1.5447

Max Act: 0.6788. Min Act: -0.0000

Data Index: 623634 (The Pile)

Max Activating Token Index: 748