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

Dataset: The Pile

Neuron 1709 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.7970. Min Act: -0.0000

Data Index: 1663687 (The Pile)

Max Activating Token Index: 954

Text #1

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.7092. Min Act: -0.0000

Data Index: 1898190 (The Pile)

Max Activating Token Index: 1004

Text #2

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.1176. Min Act: -0.0000

Data Index: 470820 (The Pile)

Max Activating Token Index: 940

Text #3

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.2380. Min Act: -0.0000

Data Index: 172291 (The Pile)

Max Activating Token Index: 503

Text #4

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.1566. Min Act: -0.0000

Data Index: 789383 (The Pile)

Max Activating Token Index: 344

Text #5

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.1084. Min Act: -0.0000

Data Index: 1736869 (The Pile)

Max Activating Token Index: 989

Text #6

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.1393. Min Act: -0.0000

Data Index: 725541 (The Pile)

Max Activating Token Index: 924

Text #7

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.0198. Min Act: -0.0000

Data Index: 1799714 (The Pile)

Max Activating Token Index: 559

Text #8

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.0459. Min Act: -0.0000

Data Index: 1434970 (The Pile)

Max Activating Token Index: 436

Text #9

Max Range: 1.7970. Min Range: -1.7970

Max Act: 0.9694. Min Act: -0.0000

Data Index: 700619 (The Pile)

Max Activating Token Index: 246

Text #10

Max Range: 1.7970. Min Range: -1.7970

Max Act: 0.9927. Min Act: -0.0000

Data Index: 1569490 (The Pile)

Max Activating Token Index: 365

Text #11

Max Range: 1.7970. Min Range: -1.7970

Max Act: 0.9789. Min Act: -0.0000

Data Index: 1286617 (The Pile)

Max Activating Token Index: 593

Text #12

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.0265. Min Act: -0.0000

Data Index: 511024 (The Pile)

Max Activating Token Index: 582

Text #13

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.0412. Min Act: -0.0000

Data Index: 715545 (The Pile)

Max Activating Token Index: 872

Text #14

Max Range: 1.7970. Min Range: -1.7970

Max Act: 0.7238. Min Act: -0.0000

Data Index: 238067 (The Pile)

Max Activating Token Index: 217

Text #15

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.0183. Min Act: -0.0000

Data Index: 92710 (The Pile)

Max Activating Token Index: 246

Text #16

Max Range: 1.7970. Min Range: -1.7970

Max Act: 0.9882. Min Act: -0.0000

Data Index: 1061608 (The Pile)

Max Activating Token Index: 403

Text #17

Max Range: 1.7970. Min Range: -1.7970

Max Act: 0.8726. Min Act: -0.0000

Data Index: 680556 (The Pile)

Max Activating Token Index: 361

Text #18

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.0037. Min Act: -0.0000

Data Index: 1137382 (The Pile)

Max Activating Token Index: 43

Text #19

Max Range: 1.7970. Min Range: -1.7970

Max Act: 0.9955. Min Act: -0.0000

Data Index: 193938 (The Pile)

Max Activating Token Index: 238