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

Dataset: The Pile

Neuron 4407 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: 0.7324. Min Range: -0.7324

Max Act: 0.7324. Min Act: -0.0000

Data Index: 326050 (The Pile)

Max Activating Token Index: 484

Text #1

Max Range: 0.7324. Min Range: -0.7324

Max Act: 0.5986. Min Act: -0.0000

Data Index: 1389122 (The Pile)

Max Activating Token Index: 43

Text #2

Max Range: 0.7324. Min Range: -0.7324

Max Act: 0.5596. Min Act: -0.0000

Data Index: 1514625 (The Pile)

Max Activating Token Index: 378

Text #3

Max Range: 0.7324. Min Range: -0.7324

Max Act: 0.5932. Min Act: -0.0000

Data Index: 1556609 (The Pile)

Max Activating Token Index: 133

Text #4

Max Range: 0.7324. Min Range: -0.7324

Max Act: 0.6351. Min Act: 0.0000

Data Index: 1666730 (The Pile)

Max Activating Token Index: 686

Text #5

Max Range: 0.7324. Min Range: -0.7324

Max Act: 0.5063. Min Act: -0.0000

Data Index: 772680 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.7324. Min Range: -0.7324

Max Act: 0.5673. Min Act: -0.0000

Data Index: 483587 (The Pile)

Max Activating Token Index: 769

Text #7

Max Range: 0.7324. Min Range: -0.7324

Max Act: 0.6424. Min Act: -0.0000

Data Index: 1780424 (The Pile)

Max Activating Token Index: 198

Text #8

Max Range: 0.7324. Min Range: -0.7324

Max Act: 0.6158. Min Act: -0.0000

Data Index: 683386 (The Pile)

Max Activating Token Index: 993

Text #9

Max Range: 0.7324. Min Range: -0.7324

Max Act: 0.5279. Min Act: -0.0000

Data Index: 1049259 (The Pile)

Max Activating Token Index: 949

Text #10

Max Range: 0.7324. Min Range: -0.7324

Max Act: 0.5771. Min Act: -0.0000

Data Index: 673772 (The Pile)

Max Activating Token Index: 1015

Text #11

Max Range: 0.7324. Min Range: -0.7324

Max Act: 0.5794. Min Act: -0.0000

Data Index: 138445 (The Pile)

Max Activating Token Index: 120

Text #12

Max Range: 0.7324. Min Range: -0.7324

Max Act: 0.5477. Min Act: -0.0000

Data Index: 1828870 (The Pile)

Max Activating Token Index: 135

Text #13

Max Range: 0.7324. Min Range: -0.7324

Max Act: 0.5175. Min Act: -0.0000

Data Index: 414341 (The Pile)

Max Activating Token Index: 863

Text #14

Max Range: 0.7324. Min Range: -0.7324

Max Act: 0.5261. Min Act: 0.0000

Data Index: 184062 (The Pile)

Max Activating Token Index: 92

Text #15

Max Range: 0.7324. Min Range: -0.7324

Max Act: 0.4827. Min Act: -0.0000

Data Index: 256992 (The Pile)

Max Activating Token Index: 131

Text #16

Max Range: 0.7324. Min Range: -0.7324

Max Act: 0.5286. Min Act: -0.0000

Data Index: 1097572 (The Pile)

Max Activating Token Index: 110

Text #17

Max Range: 0.7324. Min Range: -0.7324

Max Act: 0.4941. Min Act: -0.0000

Data Index: 664639 (The Pile)

Max Activating Token Index: 117

Text #18

Max Range: 0.7324. Min Range: -0.7324

Max Act: 0.5037. Min Act: -0.0000

Data Index: 549631 (The Pile)

Max Activating Token Index: 399

Text #19

Max Range: 0.7324. Min Range: -0.7324

Max Act: 0.4432. Min Act: -0.0000

Data Index: 1319312 (The Pile)

Max Activating Token Index: 275