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

Dataset: The Pile

Neuron 482 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: 0.8360. Min Range: -0.8360

Max Act: 0.8131. Min Act: -0.0000

Data Index: 1979116 (The Pile)

Max Activating Token Index: 825

Text #1

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.8193. Min Act: -0.0000

Data Index: 155105 (The Pile)

Max Activating Token Index: 368

Text #2

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.8240. Min Act: -0.0000

Data Index: 17317 (The Pile)

Max Activating Token Index: 304

Text #3

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.8024. Min Act: -0.0000

Data Index: 1861674 (The Pile)

Max Activating Token Index: 139

Text #4

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.7491. Min Act: -0.0000

Data Index: 1178730 (The Pile)

Max Activating Token Index: 51

Text #5

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.7280. Min Act: -0.0000

Data Index: 1821633 (The Pile)

Max Activating Token Index: 321

Text #6

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.6906. Min Act: -0.0000

Data Index: 1578301 (The Pile)

Max Activating Token Index: 30

Text #7

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.6997. Min Act: -0.0000

Data Index: 923807 (The Pile)

Max Activating Token Index: 188

Text #8

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.7709. Min Act: -0.0000

Data Index: 1768178 (The Pile)

Max Activating Token Index: 736

Text #9

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.8360. Min Act: -0.0000

Data Index: 455514 (The Pile)

Max Activating Token Index: 769

Text #10

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.7202. Min Act: -0.0000

Data Index: 627652 (The Pile)

Max Activating Token Index: 123

Text #11

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.6302. Min Act: -0.0000

Data Index: 481766 (The Pile)

Max Activating Token Index: 698

Text #12

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.6025. Min Act: -0.0000

Data Index: 1095667 (The Pile)

Max Activating Token Index: 962

Text #13

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.7802. Min Act: -0.0000

Data Index: 27454 (The Pile)

Max Activating Token Index: 949

Text #14

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.6612. Min Act: -0.0000

Data Index: 545577 (The Pile)

Max Activating Token Index: 445

Text #15

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.6855. Min Act: -0.0000

Data Index: 793207 (The Pile)

Max Activating Token Index: 589

Text #16

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.6130. Min Act: -0.0000

Data Index: 1293554 (The Pile)

Max Activating Token Index: 383

Text #17

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.5861. Min Act: -0.0000

Data Index: 1527471 (The Pile)

Max Activating Token Index: 447

Text #18

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.6548. Min Act: -0.0000

Data Index: 936198 (The Pile)

Max Activating Token Index: 683

Text #19

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.5260. Min Act: -0.0000

Data Index: 1434109 (The Pile)

Max Activating Token Index: 597