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

Dataset: The Pile

Neuron 3915 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: 0.7884. Min Range: -0.7884

Max Act: 0.7752. Min Act: -0.0000

Data Index: 1745041 (The Pile)

Max Activating Token Index: 219

Text #1

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.7884. Min Act: -0.0000

Data Index: 1103202 (The Pile)

Max Activating Token Index: 989

Text #2

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.7647. Min Act: -0.0000

Data Index: 1680605 (The Pile)

Max Activating Token Index: 650

Text #3

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.7091. Min Act: -0.0000

Data Index: 625193 (The Pile)

Max Activating Token Index: 548

Text #4

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6937. Min Act: -0.0000

Data Index: 627954 (The Pile)

Max Activating Token Index: 978

Text #5

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.7465. Min Act: -0.0000

Data Index: 679444 (The Pile)

Max Activating Token Index: 343

Text #6

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.7577. Min Act: -0.0000

Data Index: 1219494 (The Pile)

Max Activating Token Index: 74

Text #7

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6854. Min Act: -0.0000

Data Index: 885800 (The Pile)

Max Activating Token Index: 975

Text #8

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6793. Min Act: -0.0000

Data Index: 1109850 (The Pile)

Max Activating Token Index: 949

Text #9

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.7193. Min Act: -0.0000

Data Index: 1178033 (The Pile)

Max Activating Token Index: 558

Text #10

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6806. Min Act: -0.0000

Data Index: 238934 (The Pile)

Max Activating Token Index: 194

Text #11

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6494. Min Act: -0.0000

Data Index: 1541991 (The Pile)

Max Activating Token Index: 547

Text #12

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6928. Min Act: -0.0000

Data Index: 396568 (The Pile)

Max Activating Token Index: 180

Text #13

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6656. Min Act: -0.0000

Data Index: 7907 (The Pile)

Max Activating Token Index: 954

Text #14

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6674. Min Act: -0.0000

Data Index: 1203286 (The Pile)

Max Activating Token Index: 443

Text #15

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.5963. Min Act: -0.0000

Data Index: 1075270 (The Pile)

Max Activating Token Index: 639

Text #16

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6802. Min Act: -0.0000

Data Index: 1255608 (The Pile)

Max Activating Token Index: 439

Text #17

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6737. Min Act: -0.0000

Data Index: 1887337 (The Pile)

Max Activating Token Index: 346

Text #18

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6585. Min Act: -0.0000

Data Index: 1146861 (The Pile)

Max Activating Token Index: 776

Text #19

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6052. Min Act: -0.0000

Data Index: 560008 (The Pile)

Max Activating Token Index: 519