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

Dataset: The Pile

Neuron 2637 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: 0.5752. Min Range: -0.5752

Max Act: 0.5752. Min Act: -0.0000

Data Index: 1164601 (The Pile)

Max Activating Token Index: 250

Text #1

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.5557. Min Act: 0.0000

Data Index: 1105553 (The Pile)

Max Activating Token Index: 629

Text #2

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.5679. Min Act: -0.0000

Data Index: 202683 (The Pile)

Max Activating Token Index: 476

Text #3

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.5285. Min Act: -0.0000

Data Index: 1927675 (The Pile)

Max Activating Token Index: 68

Text #4

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.5272. Min Act: -0.0000

Data Index: 1156568 (The Pile)

Max Activating Token Index: 553

Text #5

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.5183. Min Act: -0.0000

Data Index: 532583 (The Pile)

Max Activating Token Index: 118

Text #6

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.5123. Min Act: 0.0001

Data Index: 1839421 (The Pile)

Max Activating Token Index: 390

Text #7

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.5024. Min Act: -0.0000

Data Index: 1930513 (The Pile)

Max Activating Token Index: 19

Text #8

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.4821. Min Act: -0.0000

Data Index: 922890 (The Pile)

Max Activating Token Index: 201

Text #9

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.5159. Min Act: -0.0000

Data Index: 1775551 (The Pile)

Max Activating Token Index: 56

Text #10

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.5127. Min Act: -0.0000

Data Index: 1932242 (The Pile)

Max Activating Token Index: 703

Text #11

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.4912. Min Act: -0.0000

Data Index: 401049 (The Pile)

Max Activating Token Index: 158

Text #12

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.4761. Min Act: -0.0000

Data Index: 594966 (The Pile)

Max Activating Token Index: 581

Text #13

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.4894. Min Act: 0.0000

Data Index: 1277570 (The Pile)

Max Activating Token Index: 530

Text #14

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.4796. Min Act: -0.0000

Data Index: 1134793 (The Pile)

Max Activating Token Index: 38

Text #15

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.4791. Min Act: -0.0000

Data Index: 1917799 (The Pile)

Max Activating Token Index: 379

Text #16

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.4890. Min Act: -0.0000

Data Index: 673046 (The Pile)

Max Activating Token Index: 611

Text #17

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.4719. Min Act: -0.0000

Data Index: 1130932 (The Pile)

Max Activating Token Index: 380

Text #18

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.4570. Min Act: 0.0000

Data Index: 55565 (The Pile)

Max Activating Token Index: 993

Text #19

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.4710. Min Act: -0.0000

Data Index: 1234417 (The Pile)

Max Activating Token Index: 545