Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 767 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.7219. Min Range: -3.7219

Max Act: 3.6016. Min Act: -0.0000

Data Index: 957340 (The Pile)

Max Activating Token Index: 234

Text #1

Max Range: 3.7219. Min Range: -3.7219

Max Act: 3.5353. Min Act: -0.0000

Data Index: 1816304 (The Pile)

Max Activating Token Index: 495

Text #2

Max Range: 3.7219. Min Range: -3.7219

Max Act: 3.7219. Min Act: -0.0000

Data Index: 1693964 (The Pile)

Max Activating Token Index: 1001

Text #3

Max Range: 3.7219. Min Range: -3.7219

Max Act: 3.5029. Min Act: -0.0000

Data Index: 1274821 (The Pile)

Max Activating Token Index: 698

Text #4

Max Range: 3.7219. Min Range: -3.7219

Max Act: 3.5252. Min Act: -0.0000

Data Index: 803549 (The Pile)

Max Activating Token Index: 40

Text #5

Max Range: 3.7219. Min Range: -3.7219

Max Act: 3.4690. Min Act: -0.0000

Data Index: 1419031 (The Pile)

Max Activating Token Index: 405

Text #6

Max Range: 3.7219. Min Range: -3.7219

Max Act: 3.1079. Min Act: -0.0000

Data Index: 403948 (The Pile)

Max Activating Token Index: 887

Text #7

Max Range: 3.7219. Min Range: -3.7219

Max Act: 3.2434. Min Act: -0.0000

Data Index: 1182744 (The Pile)

Max Activating Token Index: 99

Text #8

Max Range: 3.7219. Min Range: -3.7219

Max Act: 3.1638. Min Act: -0.0000

Data Index: 528208 (The Pile)

Max Activating Token Index: 141

Text #9

Max Range: 3.7219. Min Range: -3.7219

Max Act: 2.9823. Min Act: -0.0000

Data Index: 991175 (The Pile)

Max Activating Token Index: 485

Text #10

Max Range: 3.7219. Min Range: -3.7219

Max Act: 2.8337. Min Act: -0.0000

Data Index: 1853003 (The Pile)

Max Activating Token Index: 450

Text #11

Max Range: 3.7219. Min Range: -3.7219

Max Act: 3.2501. Min Act: -0.0000

Data Index: 1341993 (The Pile)

Max Activating Token Index: 853

Text #12

Max Range: 3.7219. Min Range: -3.7219

Max Act: 2.8801. Min Act: -0.0000

Data Index: 762093 (The Pile)

Max Activating Token Index: 498

Text #13

Max Range: 3.7219. Min Range: -3.7219

Max Act: 2.7486. Min Act: -0.0000

Data Index: 1881204 (The Pile)

Max Activating Token Index: 440

Text #14

Max Range: 3.7219. Min Range: -3.7219

Max Act: 2.8757. Min Act: -0.0000

Data Index: 686716 (The Pile)

Max Activating Token Index: 565

Text #15

Max Range: 3.7219. Min Range: -3.7219

Max Act: 3.1291. Min Act: -0.0000

Data Index: 1740687 (The Pile)

Max Activating Token Index: 854

Text #16

Max Range: 3.7219. Min Range: -3.7219

Max Act: 3.1464. Min Act: -0.0000

Data Index: 1971557 (The Pile)

Max Activating Token Index: 505

Text #17

Max Range: 3.7219. Min Range: -3.7219

Max Act: 2.9999. Min Act: -0.0000

Data Index: 1184178 (The Pile)

Max Activating Token Index: 152

Text #18

Max Range: 3.7219. Min Range: -3.7219

Max Act: 2.8508. Min Act: -0.0000

Data Index: 23830 (The Pile)

Max Activating Token Index: 386

Text #19

Max Range: 3.7219. Min Range: -3.7219

Max Act: 2.8110. Min Act: -0.0000

Data Index: 812094 (The Pile)

Max Activating Token Index: 125