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

Dataset: The Pile

Neuron 4384 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: 1.8024. Min Range: -1.8024

Max Act: 1.8024. Min Act: -0.0000

Data Index: 1895790 (The Pile)

Max Activating Token Index: 472

Text #1

Max Range: 1.8024. Min Range: -1.8024

Max Act: 1.6703. Min Act: -0.0000

Data Index: 1637727 (The Pile)

Max Activating Token Index: 361

Text #2

Max Range: 1.8024. Min Range: -1.8024

Max Act: 1.5230. Min Act: -0.0000

Data Index: 1885294 (The Pile)

Max Activating Token Index: 729

Text #3

Max Range: 1.8024. Min Range: -1.8024

Max Act: 1.6038. Min Act: -0.0000

Data Index: 1665512 (The Pile)

Max Activating Token Index: 81

Text #4

Max Range: 1.8024. Min Range: -1.8024

Max Act: 1.5519. Min Act: -0.0000

Data Index: 653160 (The Pile)

Max Activating Token Index: 1007

Text #5

Max Range: 1.8024. Min Range: -1.8024

Max Act: 1.5174. Min Act: -0.0000

Data Index: 641081 (The Pile)

Max Activating Token Index: 147

Text #6

Max Range: 1.8024. Min Range: -1.8024

Max Act: 1.5029. Min Act: -0.0000

Data Index: 907847 (The Pile)

Max Activating Token Index: 261

Text #7

Max Range: 1.8024. Min Range: -1.8024

Max Act: 1.5688. Min Act: -0.0000

Data Index: 680394 (The Pile)

Max Activating Token Index: 102

Text #8

Max Range: 1.8024. Min Range: -1.8024

Max Act: 1.4844. Min Act: -0.0000

Data Index: 1548318 (The Pile)

Max Activating Token Index: 47

Text #9

Max Range: 1.8024. Min Range: -1.8024

Max Act: 1.5537. Min Act: -0.0000

Data Index: 855571 (The Pile)

Max Activating Token Index: 742

Text #10

Max Range: 1.8024. Min Range: -1.8024

Max Act: 1.4467. Min Act: -0.0000

Data Index: 1948283 (The Pile)

Max Activating Token Index: 571

Text #11

Max Range: 1.8024. Min Range: -1.8024

Max Act: 1.4087. Min Act: -0.0000

Data Index: 721768 (The Pile)

Max Activating Token Index: 308

Text #12

Max Range: 1.8024. Min Range: -1.8024

Max Act: 1.3347. Min Act: -0.0000

Data Index: 1374417 (The Pile)

Max Activating Token Index: 289

Text #13

Max Range: 1.8024. Min Range: -1.8024

Max Act: 1.2955. Min Act: -0.0000

Data Index: 673157 (The Pile)

Max Activating Token Index: 720

Text #14

Max Range: 1.8024. Min Range: -1.8024

Max Act: 1.3712. Min Act: -0.0000

Data Index: 1064230 (The Pile)

Max Activating Token Index: 1015

Text #15

Max Range: 1.8024. Min Range: -1.8024

Max Act: 1.3036. Min Act: -0.0000

Data Index: 175923 (The Pile)

Max Activating Token Index: 780

Text #16

Max Range: 1.8024. Min Range: -1.8024

Max Act: 1.2769. Min Act: -0.0000

Data Index: 1781049 (The Pile)

Max Activating Token Index: 882

Text #17

Max Range: 1.8024. Min Range: -1.8024

Max Act: 1.3449. Min Act: -0.0000

Data Index: 1101246 (The Pile)

Max Activating Token Index: 792

Text #18

Max Range: 1.8024. Min Range: -1.8024

Max Act: 1.2633. Min Act: -0.0000

Data Index: 1845155 (The Pile)

Max Activating Token Index: 917

Text #19

Max Range: 1.8024. Min Range: -1.8024

Max Act: 1.3526. Min Act: -0.0000

Data Index: 705372 (The Pile)

Max Activating Token Index: 703