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

Dataset: The Pile

Neuron 52 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.5129. Min Act: -0.0000

Data Index: 1008643 (The Pile)

Max Activating Token Index: 340

Text #1

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.4613. Min Act: -0.0000

Data Index: 1577119 (The Pile)

Max Activating Token Index: 530

Text #2

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.4601. Min Act: -0.0000

Data Index: 1975745 (The Pile)

Max Activating Token Index: 710

Text #3

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.4029. Min Act: -0.0000

Data Index: 1943817 (The Pile)

Max Activating Token Index: 722

Text #4

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.2549. Min Act: -0.0000

Data Index: 1374276 (The Pile)

Max Activating Token Index: 279

Text #5

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.2173. Min Act: -0.0000

Data Index: 1383828 (The Pile)

Max Activating Token Index: 438

Text #6

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.2093. Min Act: -0.0000

Data Index: 700477 (The Pile)

Max Activating Token Index: 411

Text #7

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.2452. Min Act: -0.0000

Data Index: 514839 (The Pile)

Max Activating Token Index: 379

Text #8

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.2464. Min Act: -0.0000

Data Index: 165183 (The Pile)

Max Activating Token Index: 494

Text #9

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.1389. Min Act: -0.0000

Data Index: 1668533 (The Pile)

Max Activating Token Index: 102

Text #10

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.0899. Min Act: -0.0000

Data Index: 521843 (The Pile)

Max Activating Token Index: 369

Text #11

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.2103. Min Act: -0.0000

Data Index: 1848209 (The Pile)

Max Activating Token Index: 530

Text #12

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.1688. Min Act: -0.0000

Data Index: 370550 (The Pile)

Max Activating Token Index: 852

Text #13

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.1662. Min Act: -0.0000

Data Index: 1807867 (The Pile)

Max Activating Token Index: 593

Text #14

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.1249. Min Act: -0.0000

Data Index: 1898999 (The Pile)

Max Activating Token Index: 210

Text #15

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.2145. Min Act: -0.0000

Data Index: 1415863 (The Pile)

Max Activating Token Index: 473

Text #16

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.0244. Min Act: -0.0000

Data Index: 1398597 (The Pile)

Max Activating Token Index: 582

Text #17

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.1193. Min Act: -0.0000

Data Index: 45328 (The Pile)

Max Activating Token Index: 928

Text #18

Max Range: 1.5129. Min Range: -1.5129

Max Act: 0.9810. Min Act: -0.0000

Data Index: 1220581 (The Pile)

Max Activating Token Index: 742

Text #19

Max Range: 1.5129. Min Range: -1.5129

Max Act: 1.0714. Min Act: -0.0000

Data Index: 204705 (The Pile)

Max Activating Token Index: 8