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

Dataset: The Pile

Neuron 2287 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.9467. Min Act: -0.0000

Data Index: 1071963 (The Pile)

Max Activating Token Index: 571

Text #1

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.9025. Min Act: -0.0000

Data Index: 104207 (The Pile)

Max Activating Token Index: 491

Text #2

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.9266. Min Act: -0.0000

Data Index: 658906 (The Pile)

Max Activating Token Index: 87

Text #3

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.9098. Min Act: -0.0000

Data Index: 1001602 (The Pile)

Max Activating Token Index: 375

Text #4

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.9150. Min Act: -0.0000

Data Index: 1479185 (The Pile)

Max Activating Token Index: 5

Text #5

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.8986. Min Act: -0.0000

Data Index: 847806 (The Pile)

Max Activating Token Index: 391

Text #6

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.8238. Min Act: -0.0000

Data Index: 1859377 (The Pile)

Max Activating Token Index: 491

Text #7

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.8374. Min Act: -0.0000

Data Index: 944231 (The Pile)

Max Activating Token Index: 476

Text #8

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.8238. Min Act: -0.0000

Data Index: 3564 (The Pile)

Max Activating Token Index: 281

Text #9

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.8529. Min Act: -0.0000

Data Index: 959328 (The Pile)

Max Activating Token Index: 421

Text #10

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.8539. Min Act: -0.0000

Data Index: 1768662 (The Pile)

Max Activating Token Index: 448

Text #11

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.8338. Min Act: -0.0000

Data Index: 1552446 (The Pile)

Max Activating Token Index: 413

Text #12

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.8339. Min Act: 0.0000

Data Index: 1899469 (The Pile)

Max Activating Token Index: 944

Text #13

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.8409. Min Act: -0.0000

Data Index: 778482 (The Pile)

Max Activating Token Index: 170

Text #14

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.7902. Min Act: -0.0000

Data Index: 1649474 (The Pile)

Max Activating Token Index: 481

Text #15

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.8247. Min Act: -0.0000

Data Index: 672444 (The Pile)

Max Activating Token Index: 78

Text #16

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.7307. Min Act: -0.0000

Data Index: 1462255 (The Pile)

Max Activating Token Index: 929

Text #17

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.7205. Min Act: -0.0000

Data Index: 71250 (The Pile)

Max Activating Token Index: 160

Text #18

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6475. Min Act: -0.0000

Data Index: 1127362 (The Pile)

Max Activating Token Index: 932

Text #19

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.8201. Min Act: 0.0000

Data Index: 847071 (The Pile)

Max Activating Token Index: 476