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

Dataset: The Pile

Neuron 3562 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.1291. Min Act: -0.0000

Data Index: 1895593 (The Pile)

Max Activating Token Index: 792

Text #1

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.1230. Min Act: -0.0000

Data Index: 1588553 (The Pile)

Max Activating Token Index: 76

Text #2

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0986. Min Act: -0.0000

Data Index: 128372 (The Pile)

Max Activating Token Index: 823

Text #3

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.1248. Min Act: -0.0000

Data Index: 67336 (The Pile)

Max Activating Token Index: 357

Text #4

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.1003. Min Act: -0.0000

Data Index: 1806159 (The Pile)

Max Activating Token Index: 1016

Text #5

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.1094. Min Act: -0.0000

Data Index: 1831626 (The Pile)

Max Activating Token Index: 38

Text #6

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.1049. Min Act: -0.0000

Data Index: 1904621 (The Pile)

Max Activating Token Index: 278

Text #7

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.1036. Min Act: -0.0000

Data Index: 981511 (The Pile)

Max Activating Token Index: 752

Text #8

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0849. Min Act: -0.0000

Data Index: 1783199 (The Pile)

Max Activating Token Index: 887

Text #9

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.1025. Min Act: -0.0000

Data Index: 1030623 (The Pile)

Max Activating Token Index: 947

Text #10

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0926. Min Act: -0.0000

Data Index: 615769 (The Pile)

Max Activating Token Index: 679

Text #11

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0443. Min Act: -0.0000

Data Index: 298991 (The Pile)

Max Activating Token Index: 786

Text #12

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0949. Min Act: -0.0000

Data Index: 351955 (The Pile)

Max Activating Token Index: 71

Text #13

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0961. Min Act: -0.0000

Data Index: 67557 (The Pile)

Max Activating Token Index: 544

Text #14

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0969. Min Act: -0.0000

Data Index: 789565 (The Pile)

Max Activating Token Index: 504

Text #15

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0822. Min Act: -0.0000

Data Index: 1849785 (The Pile)

Max Activating Token Index: 575

Text #16

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0752. Min Act: -0.0000

Data Index: 189806 (The Pile)

Max Activating Token Index: 170

Text #17

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0825. Min Act: -0.0000

Data Index: 192007 (The Pile)

Max Activating Token Index: 88

Text #18

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0676. Min Act: -0.0000

Data Index: 1829541 (The Pile)

Max Activating Token Index: 965

Text #19

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0910. Min Act: -0.0000

Data Index: 1269588 (The Pile)

Max Activating Token Index: 320