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

Dataset: The Pile

Neuron 2405 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5568. Min Range: -0.5568

Max Act: 0.5568. Min Act: -0.0000

Data Index: 72255 (The Pile)

Max Activating Token Index: 323

Text #1

Max Range: 0.5568. Min Range: -0.5568

Max Act: 0.5262. Min Act: -0.0000

Data Index: 1053727 (The Pile)

Max Activating Token Index: 899

Text #2

Max Range: 0.5568. Min Range: -0.5568

Max Act: 0.4785. Min Act: -0.0000

Data Index: 1124814 (The Pile)

Max Activating Token Index: 728

Text #3

Max Range: 0.5568. Min Range: -0.5568

Max Act: 0.5270. Min Act: -0.0000

Data Index: 1575044 (The Pile)

Max Activating Token Index: 63

Text #4

Max Range: 0.5568. Min Range: -0.5568

Max Act: 0.4183. Min Act: -0.0000

Data Index: 1044312 (The Pile)

Max Activating Token Index: 631

Text #5

Max Range: 0.5568. Min Range: -0.5568

Max Act: 0.4450. Min Act: -0.0000

Data Index: 810946 (The Pile)

Max Activating Token Index: 965

Text #6

Max Range: 0.5568. Min Range: -0.5568

Max Act: 0.4560. Min Act: -0.0000

Data Index: 618824 (The Pile)

Max Activating Token Index: 659

Text #7

Max Range: 0.5568. Min Range: -0.5568

Max Act: 0.4654. Min Act: -0.0000

Data Index: 923664 (The Pile)

Max Activating Token Index: 86

Text #8

Max Range: 0.5568. Min Range: -0.5568

Max Act: 0.4769. Min Act: -0.0000

Data Index: 1501909 (The Pile)

Max Activating Token Index: 148

Text #9

Max Range: 0.5568. Min Range: -0.5568

Max Act: 0.4068. Min Act: -0.0000

Data Index: 1241902 (The Pile)

Max Activating Token Index: 796

Text #10

Max Range: 0.5568. Min Range: -0.5568

Max Act: 0.4145. Min Act: -0.0000

Data Index: 1548217 (The Pile)

Max Activating Token Index: 214

Text #11

Max Range: 0.5568. Min Range: -0.5568

Max Act: 0.4204. Min Act: -0.0000

Data Index: 709906 (The Pile)

Max Activating Token Index: 430

Text #12

Max Range: 0.5568. Min Range: -0.5568

Max Act: 0.4264. Min Act: -0.0000

Data Index: 167971 (The Pile)

Max Activating Token Index: 171

Text #13

Max Range: 0.5568. Min Range: -0.5568

Max Act: 0.4384. Min Act: -0.0000

Data Index: 1887451 (The Pile)

Max Activating Token Index: 126

Text #14

Max Range: 0.5568. Min Range: -0.5568

Max Act: 0.4005. Min Act: -0.0000

Data Index: 853747 (The Pile)

Max Activating Token Index: 133

Text #15

Max Range: 0.5568. Min Range: -0.5568

Max Act: 0.4106. Min Act: -0.0000

Data Index: 546609 (The Pile)

Max Activating Token Index: 856

Text #16

Max Range: 0.5568. Min Range: -0.5568

Max Act: 0.4268. Min Act: -0.0000

Data Index: 487690 (The Pile)

Max Activating Token Index: 969

Text #17

Max Range: 0.5568. Min Range: -0.5568

Max Act: 0.4046. Min Act: -0.0000

Data Index: 1048543 (The Pile)

Max Activating Token Index: 230

Text #18

Max Range: 0.5568. Min Range: -0.5568

Max Act: 0.3692. Min Act: -0.0000

Data Index: 1816487 (The Pile)

Max Activating Token Index: 929

Text #19

Max Range: 0.5568. Min Range: -0.5568

Max Act: 0.3924. Min Act: -0.0000

Data Index: 887425 (The Pile)

Max Activating Token Index: 454