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

Dataset: The Pile

Neuron 3640 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: 0.5097. Min Range: -0.5097

Max Act: 0.4988. Min Act: -0.0000

Data Index: 1750733 (The Pile)

Max Activating Token Index: 367

Text #1

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4760. Min Act: -0.0000

Data Index: 1894959 (The Pile)

Max Activating Token Index: 573

Text #2

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4772. Min Act: -0.0000

Data Index: 189517 (The Pile)

Max Activating Token Index: 699

Text #3

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.5097. Min Act: -0.0000

Data Index: 879060 (The Pile)

Max Activating Token Index: 878

Text #4

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4853. Min Act: -0.0000

Data Index: 824729 (The Pile)

Max Activating Token Index: 991

Text #5

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4600. Min Act: -0.0000

Data Index: 704106 (The Pile)

Max Activating Token Index: 462

Text #6

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4745. Min Act: -0.0000

Data Index: 165016 (The Pile)

Max Activating Token Index: 231

Text #7

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4819. Min Act: -0.0000

Data Index: 482964 (The Pile)

Max Activating Token Index: 189

Text #8

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4384. Min Act: 0.0000

Data Index: 462284 (The Pile)

Max Activating Token Index: 661

Text #9

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4395. Min Act: -0.0000

Data Index: 1900270 (The Pile)

Max Activating Token Index: 910

Text #10

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4745. Min Act: -0.0000

Data Index: 912232 (The Pile)

Max Activating Token Index: 651

Text #11

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4418. Min Act: -0.0000

Data Index: 516913 (The Pile)

Max Activating Token Index: 241

Text #12

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4539. Min Act: -0.0000

Data Index: 833807 (The Pile)

Max Activating Token Index: 71

Text #13

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4621. Min Act: 0.0000

Data Index: 1882757 (The Pile)

Max Activating Token Index: 149

Text #14

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4429. Min Act: 0.0000

Data Index: 1832081 (The Pile)

Max Activating Token Index: 799

Text #15

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4134. Min Act: -0.0000

Data Index: 861104 (The Pile)

Max Activating Token Index: 552

Text #16

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4177. Min Act: -0.0000

Data Index: 599308 (The Pile)

Max Activating Token Index: 722

Text #17

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4280. Min Act: -0.0000

Data Index: 1929857 (The Pile)

Max Activating Token Index: 581

Text #18

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.3869. Min Act: -0.0000

Data Index: 551779 (The Pile)

Max Activating Token Index: 443

Text #19

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4103. Min Act: -0.0000

Data Index: 883604 (The Pile)

Max Activating Token Index: 483