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

Dataset: The Pile

Neuron 3149 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: 1.5144. Min Range: -1.5144

Max Act: 1.5144. Min Act: -0.0000

Data Index: 968291 (The Pile)

Max Activating Token Index: 579

Text #1

Max Range: 1.5144. Min Range: -1.5144

Max Act: 1.5055. Min Act: -0.0000

Data Index: 1132340 (The Pile)

Max Activating Token Index: 18

Text #2

Max Range: 1.5144. Min Range: -1.5144

Max Act: 1.2092. Min Act: -0.0000

Data Index: 1496823 (The Pile)

Max Activating Token Index: 481

Text #3

Max Range: 1.5144. Min Range: -1.5144

Max Act: 1.1762. Min Act: -0.0000

Data Index: 1645993 (The Pile)

Max Activating Token Index: 534

Text #4

Max Range: 1.5144. Min Range: -1.5144

Max Act: 1.0611. Min Act: -0.0000

Data Index: 1958896 (The Pile)

Max Activating Token Index: 614

Text #5

Max Range: 1.5144. Min Range: -1.5144

Max Act: 0.9796. Min Act: -0.0000

Data Index: 1764624 (The Pile)

Max Activating Token Index: 593

Text #6

Max Range: 1.5144. Min Range: -1.5144

Max Act: 0.9493. Min Act: -0.0000

Data Index: 1855854 (The Pile)

Max Activating Token Index: 46

Text #7

Max Range: 1.5144. Min Range: -1.5144

Max Act: 1.0191. Min Act: -0.0000

Data Index: 1008656 (The Pile)

Max Activating Token Index: 616

Text #8

Max Range: 1.5144. Min Range: -1.5144

Max Act: 0.9883. Min Act: -0.0000

Data Index: 1673906 (The Pile)

Max Activating Token Index: 430

Text #9

Max Range: 1.5144. Min Range: -1.5144

Max Act: 0.9856. Min Act: -0.0000

Data Index: 1675725 (The Pile)

Max Activating Token Index: 500

Text #10

Max Range: 1.5144. Min Range: -1.5144

Max Act: 1.0919. Min Act: -0.0000

Data Index: 1103678 (The Pile)

Max Activating Token Index: 509

Text #11

Max Range: 1.5144. Min Range: -1.5144

Max Act: 1.0431. Min Act: -0.0000

Data Index: 78684 (The Pile)

Max Activating Token Index: 476

Text #12

Max Range: 1.5144. Min Range: -1.5144

Max Act: 0.9503. Min Act: -0.0000

Data Index: 76241 (The Pile)

Max Activating Token Index: 109

Text #13

Max Range: 1.5144. Min Range: -1.5144

Max Act: 0.9404. Min Act: -0.0000

Data Index: 1033405 (The Pile)

Max Activating Token Index: 585

Text #14

Max Range: 1.5144. Min Range: -1.5144

Max Act: 1.0503. Min Act: -0.0000

Data Index: 297982 (The Pile)

Max Activating Token Index: 172

Text #15

Max Range: 1.5144. Min Range: -1.5144

Max Act: 0.8864. Min Act: -0.0000

Data Index: 878288 (The Pile)

Max Activating Token Index: 795

Text #16

Max Range: 1.5144. Min Range: -1.5144

Max Act: 0.9259. Min Act: -0.0000

Data Index: 1201332 (The Pile)

Max Activating Token Index: 984

Text #17

Max Range: 1.5144. Min Range: -1.5144

Max Act: 0.8675. Min Act: -0.0000

Data Index: 1051492 (The Pile)

Max Activating Token Index: 453

Text #18

Max Range: 1.5144. Min Range: -1.5144

Max Act: 0.9821. Min Act: -0.0000

Data Index: 143664 (The Pile)

Max Activating Token Index: 1008

Text #19

Max Range: 1.5144. Min Range: -1.5144

Max Act: 0.7944. Min Act: -0.0000

Data Index: 1431028 (The Pile)

Max Activating Token Index: 1002