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

Dataset: The Pile

Neuron 3463 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: 0.8407. Min Range: -0.8407

Max Act: 0.8407. Min Act: -0.0000

Data Index: 1049501 (The Pile)

Max Activating Token Index: 459

Text #1

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.8166. Min Act: -0.0000

Data Index: 1398217 (The Pile)

Max Activating Token Index: 520

Text #2

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.7073. Min Act: -0.0000

Data Index: 1830611 (The Pile)

Max Activating Token Index: 638

Text #3

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.6754. Min Act: -0.0000

Data Index: 1311337 (The Pile)

Max Activating Token Index: 698

Text #4

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.6934. Min Act: -0.0000

Data Index: 433440 (The Pile)

Max Activating Token Index: 211

Text #5

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.6714. Min Act: -0.0000

Data Index: 473240 (The Pile)

Max Activating Token Index: 241

Text #6

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.6858. Min Act: -0.0000

Data Index: 1866528 (The Pile)

Max Activating Token Index: 550

Text #7

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.6512. Min Act: -0.0000

Data Index: 1823872 (The Pile)

Max Activating Token Index: 41

Text #8

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.6606. Min Act: -0.0000

Data Index: 105042 (The Pile)

Max Activating Token Index: 427

Text #9

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.6966. Min Act: -0.0000

Data Index: 1901856 (The Pile)

Max Activating Token Index: 1018

Text #10

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.6477. Min Act: -0.0000

Data Index: 291214 (The Pile)

Max Activating Token Index: 908

Text #11

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.6746. Min Act: -0.0000

Data Index: 1883401 (The Pile)

Max Activating Token Index: 790

Text #12

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.6767. Min Act: -0.0000

Data Index: 1198753 (The Pile)

Max Activating Token Index: 56

Text #13

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.6440. Min Act: -0.0000

Data Index: 1349731 (The Pile)

Max Activating Token Index: 866

Text #14

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.6401. Min Act: -0.0000

Data Index: 222871 (The Pile)

Max Activating Token Index: 450

Text #15

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.6510. Min Act: -0.0000

Data Index: 1177065 (The Pile)

Max Activating Token Index: 456

Text #16

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.6571. Min Act: -0.0000

Data Index: 538010 (The Pile)

Max Activating Token Index: 422

Text #17

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.6119. Min Act: -0.0000

Data Index: 1473170 (The Pile)

Max Activating Token Index: 422

Text #18

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.5930. Min Act: -0.0000

Data Index: 1807254 (The Pile)

Max Activating Token Index: 120

Text #19

Max Range: 0.8407. Min Range: -0.8407

Max Act: 0.6258. Min Act: -0.0000

Data Index: 63391 (The Pile)

Max Activating Token Index: 166