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

Dataset: The Pile

Neuron 3200 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: 3.2912. Min Range: -3.2912

Max Act: 3.2912. Min Act: -0.0000

Data Index: 1501427 (The Pile)

Max Activating Token Index: 345

Text #1

Max Range: 3.2912. Min Range: -3.2912

Max Act: 1.6069. Min Act: -0.0000

Data Index: 256235 (The Pile)

Max Activating Token Index: 533

Text #2

Max Range: 3.2912. Min Range: -3.2912

Max Act: 1.0694. Min Act: -0.0000

Data Index: 288474 (The Pile)

Max Activating Token Index: 915

Text #3

Max Range: 3.2912. Min Range: -3.2912

Max Act: 1.5956. Min Act: -0.0000

Data Index: 1651753 (The Pile)

Max Activating Token Index: 62

Text #4

Max Range: 3.2912. Min Range: -3.2912

Max Act: 1.2066. Min Act: -0.0000

Data Index: 1137142 (The Pile)

Max Activating Token Index: 244

Text #5

Max Range: 3.2912. Min Range: -3.2912

Max Act: 0.7237. Min Act: -0.0000

Data Index: 464747 (The Pile)

Max Activating Token Index: 916

Text #6

Max Range: 3.2912. Min Range: -3.2912

Max Act: 0.9947. Min Act: -0.0000

Data Index: 74288 (The Pile)

Max Activating Token Index: 101

Text #7

Max Range: 3.2912. Min Range: -3.2912

Max Act: 0.7502. Min Act: -0.0000

Data Index: 1515451 (The Pile)

Max Activating Token Index: 44

Text #8

Max Range: 3.2912. Min Range: -3.2912

Max Act: 1.1156. Min Act: -0.0000

Data Index: 798730 (The Pile)

Max Activating Token Index: 45

Text #9

Max Range: 3.2912. Min Range: -3.2912

Max Act: 0.8675. Min Act: -0.0000

Data Index: 1284383 (The Pile)

Max Activating Token Index: 312

Text #10

Max Range: 3.2912. Min Range: -3.2912

Max Act: 0.6838. Min Act: -0.0000

Data Index: 267260 (The Pile)

Max Activating Token Index: 434

Text #11

Max Range: 3.2912. Min Range: -3.2912

Max Act: 0.7379. Min Act: -0.0000

Data Index: 571130 (The Pile)

Max Activating Token Index: 72

Text #12

Max Range: 3.2912. Min Range: -3.2912

Max Act: 0.6222. Min Act: -0.0000

Data Index: 341588 (The Pile)

Max Activating Token Index: 797

Text #13

Max Range: 3.2912. Min Range: -3.2912

Max Act: 0.7336. Min Act: -0.0000

Data Index: 129083 (The Pile)

Max Activating Token Index: 872

Text #14

Max Range: 3.2912. Min Range: -3.2912

Max Act: 0.7819. Min Act: -0.0000

Data Index: 1236390 (The Pile)

Max Activating Token Index: 519

Text #15

Max Range: 3.2912. Min Range: -3.2912

Max Act: 0.8190. Min Act: -0.0000

Data Index: 1480432 (The Pile)

Max Activating Token Index: 497

Text #16

Max Range: 3.2912. Min Range: -3.2912

Max Act: 0.6776. Min Act: -0.0000

Data Index: 664237 (The Pile)

Max Activating Token Index: 669

Text #17

Max Range: 3.2912. Min Range: -3.2912

Max Act: 0.7109. Min Act: -0.0000

Data Index: 1928350 (The Pile)

Max Activating Token Index: 722

Text #18

Max Range: 3.2912. Min Range: -3.2912

Max Act: 0.5535. Min Act: -0.0000

Data Index: 233336 (The Pile)

Max Activating Token Index: 1020

Text #19

Max Range: 3.2912. Min Range: -3.2912

Max Act: 0.6393. Min Act: -0.0000

Data Index: 520258 (The Pile)

Max Activating Token Index: 998