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

Dataset: The Pile

Neuron 2256 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: 0.7381. Min Range: -0.7381

Max Act: 0.7381. Min Act: -0.0000

Data Index: 532065 (The Pile)

Max Activating Token Index: 13

Text #1

Max Range: 0.7381. Min Range: -0.7381

Max Act: 0.7015. Min Act: -0.0000

Data Index: 1836872 (The Pile)

Max Activating Token Index: 924

Text #2

Max Range: 0.7381. Min Range: -0.7381

Max Act: 0.6020. Min Act: -0.0000

Data Index: 1822042 (The Pile)

Max Activating Token Index: 831

Text #3

Max Range: 0.7381. Min Range: -0.7381

Max Act: 0.6050. Min Act: -0.0000

Data Index: 133924 (The Pile)

Max Activating Token Index: 294

Text #4

Max Range: 0.7381. Min Range: -0.7381

Max Act: 0.6005. Min Act: -0.0000

Data Index: 1921395 (The Pile)

Max Activating Token Index: 177

Text #5

Max Range: 0.7381. Min Range: -0.7381

Max Act: 0.5884. Min Act: -0.0000

Data Index: 1638738 (The Pile)

Max Activating Token Index: 403

Text #6

Max Range: 0.7381. Min Range: -0.7381

Max Act: 0.6062. Min Act: -0.0000

Data Index: 1828033 (The Pile)

Max Activating Token Index: 72

Text #7

Max Range: 0.7381. Min Range: -0.7381

Max Act: 0.5274. Min Act: -0.0000

Data Index: 1621277 (The Pile)

Max Activating Token Index: 499

Text #8

Max Range: 0.7381. Min Range: -0.7381

Max Act: 0.5596. Min Act: -0.0000

Data Index: 736476 (The Pile)

Max Activating Token Index: 227

Text #9

Max Range: 0.7381. Min Range: -0.7381

Max Act: 0.5022. Min Act: -0.0000

Data Index: 806931 (The Pile)

Max Activating Token Index: 47

Text #10

Max Range: 0.7381. Min Range: -0.7381

Max Act: 0.5411. Min Act: -0.0000

Data Index: 954143 (The Pile)

Max Activating Token Index: 342

Text #11

Max Range: 0.7381. Min Range: -0.7381

Max Act: 0.5227. Min Act: -0.0000

Data Index: 978753 (The Pile)

Max Activating Token Index: 58

Text #12

Max Range: 0.7381. Min Range: -0.7381

Max Act: 0.5456. Min Act: -0.0000

Data Index: 1256210 (The Pile)

Max Activating Token Index: 304

Text #13

Max Range: 0.7381. Min Range: -0.7381

Max Act: 0.5278. Min Act: -0.0000

Data Index: 154574 (The Pile)

Max Activating Token Index: 503

Text #14

Max Range: 0.7381. Min Range: -0.7381

Max Act: 0.5137. Min Act: -0.0000

Data Index: 1589905 (The Pile)

Max Activating Token Index: 115

Text #15

Max Range: 0.7381. Min Range: -0.7381

Max Act: 0.4821. Min Act: -0.0000

Data Index: 1065043 (The Pile)

Max Activating Token Index: 1001

Text #16

Max Range: 0.7381. Min Range: -0.7381

Max Act: 0.5160. Min Act: -0.0000

Data Index: 1627545 (The Pile)

Max Activating Token Index: 565

Text #17

Max Range: 0.7381. Min Range: -0.7381

Max Act: 0.5473. Min Act: -0.0000

Data Index: 1061547 (The Pile)

Max Activating Token Index: 395

Text #18

Max Range: 0.7381. Min Range: -0.7381

Max Act: 0.5396. Min Act: -0.0000

Data Index: 53151 (The Pile)

Max Activating Token Index: 497

Text #19

Max Range: 0.7381. Min Range: -0.7381

Max Act: 0.5329. Min Act: -0.0000

Data Index: 1458482 (The Pile)

Max Activating Token Index: 514