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

Dataset: The Pile

Neuron 2613 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.1073. Min Act: -0.0000

Data Index: 1044245 (The Pile)

Max Activating Token Index: 779

Text #1

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.1098. Min Act: -0.0000

Data Index: 1303310 (The Pile)

Max Activating Token Index: 352

Text #2

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.1059. Min Act: -0.0000

Data Index: 189491 (The Pile)

Max Activating Token Index: 715

Text #3

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.1093. Min Act: -0.0000

Data Index: 190810 (The Pile)

Max Activating Token Index: 11

Text #4

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.1033. Min Act: -0.0000

Data Index: 768222 (The Pile)

Max Activating Token Index: 775

Text #5

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0965. Min Act: -0.0000

Data Index: 1312740 (The Pile)

Max Activating Token Index: 446

Text #6

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0871. Min Act: -0.0000

Data Index: 348038 (The Pile)

Max Activating Token Index: 537

Text #7

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0931. Min Act: -0.0000

Data Index: 1739133 (The Pile)

Max Activating Token Index: 291

Text #8

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0956. Min Act: -0.0000

Data Index: 514124 (The Pile)

Max Activating Token Index: 626

Text #9

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0910. Min Act: -0.0000

Data Index: 320499 (The Pile)

Max Activating Token Index: 749

Text #10

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0934. Min Act: -0.0000

Data Index: 374205 (The Pile)

Max Activating Token Index: 176

Text #11

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0932. Min Act: -0.0000

Data Index: 1308856 (The Pile)

Max Activating Token Index: 158

Text #12

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0962. Min Act: -0.0000

Data Index: 614925 (The Pile)

Max Activating Token Index: 158

Text #13

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0919. Min Act: -0.0000

Data Index: 224579 (The Pile)

Max Activating Token Index: 810

Text #14

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0931. Min Act: -0.0000

Data Index: 509373 (The Pile)

Max Activating Token Index: 859

Text #15

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0932. Min Act: -0.0000

Data Index: 1496686 (The Pile)

Max Activating Token Index: 338

Text #16

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0918. Min Act: -0.0000

Data Index: 1538213 (The Pile)

Max Activating Token Index: 722

Text #17

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0930. Min Act: -0.0000

Data Index: 103660 (The Pile)

Max Activating Token Index: 21

Text #18

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0936. Min Act: -0.0000

Data Index: 1513674 (The Pile)

Max Activating Token Index: 580

Text #19

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0879. Min Act: -0.0000

Data Index: 1935187 (The Pile)

Max Activating Token Index: 855