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

Dataset: The Pile

Neuron 568 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.7703. Min Act: -0.0000

Data Index: 851779 (The Pile)

Max Activating Token Index: 323

Text #1

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.6919. Min Act: -0.0000

Data Index: 1346048 (The Pile)

Max Activating Token Index: 596

Text #2

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.6572. Min Act: -0.0000

Data Index: 707995 (The Pile)

Max Activating Token Index: 578

Text #3

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.6053. Min Act: -0.0000

Data Index: 115588 (The Pile)

Max Activating Token Index: 160

Text #4

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.5885. Min Act: -0.0000

Data Index: 1109372 (The Pile)

Max Activating Token Index: 1010

Text #5

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.5928. Min Act: -0.0000

Data Index: 1009401 (The Pile)

Max Activating Token Index: 315

Text #6

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.6251. Min Act: -0.0000

Data Index: 1667743 (The Pile)

Max Activating Token Index: 938

Text #7

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.5969. Min Act: -0.0000

Data Index: 1998707 (The Pile)

Max Activating Token Index: 596

Text #8

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.5799. Min Act: -0.0000

Data Index: 1408844 (The Pile)

Max Activating Token Index: 522

Text #9

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.5383. Min Act: -0.0000

Data Index: 97070 (The Pile)

Max Activating Token Index: 928

Text #10

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.6169. Min Act: -0.0000

Data Index: 689700 (The Pile)

Max Activating Token Index: 885

Text #11

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.5880. Min Act: -0.0000

Data Index: 466303 (The Pile)

Max Activating Token Index: 580

Text #12

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.6034. Min Act: -0.0000

Data Index: 1326859 (The Pile)

Max Activating Token Index: 968

Text #13

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.5332. Min Act: -0.0000

Data Index: 1421442 (The Pile)

Max Activating Token Index: 74

Text #14

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.5637. Min Act: -0.0000

Data Index: 641666 (The Pile)

Max Activating Token Index: 772

Text #15

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.5509. Min Act: -0.0000

Data Index: 1168197 (The Pile)

Max Activating Token Index: 62

Text #16

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.4745. Min Act: -0.0000

Data Index: 270369 (The Pile)

Max Activating Token Index: 1012

Text #17

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.5099. Min Act: -0.0000

Data Index: 1051677 (The Pile)

Max Activating Token Index: 885

Text #18

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.5238. Min Act: -0.0000

Data Index: 1804 (The Pile)

Max Activating Token Index: 617

Text #19

Max Range: 0.7703. Min Range: -0.7703

Max Act: 0.5189. Min Act: -0.0000

Data Index: 1485857 (The Pile)

Max Activating Token Index: 525