Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5417 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1163. Min Act: -0.0000

Data Index: 781090 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1207. Min Act: -0.0000

Data Index: 936971 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1014. Min Act: -0.0000

Data Index: 1335078 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0882. Min Act: -0.0000

Data Index: 470481 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0862. Min Act: -0.0000

Data Index: 1431527 (Python Code)

Max Activating Token Index: 310

Text #5

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1128. Min Act: -0.0000

Data Index: 1597370 (Python Code)

Max Activating Token Index: 198

Text #6

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0901. Min Act: -0.0000

Data Index: 1589719 (Python Code)

Max Activating Token Index: 925

Text #7

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0879. Min Act: -0.0000

Data Index: 919386 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0938. Min Act: -0.0000

Data Index: 340817 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0864. Min Act: -0.0000

Data Index: 808965 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0899. Min Act: -0.0000

Data Index: 866957 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0828. Min Act: -0.0000

Data Index: 1555809 (Python Code)

Max Activating Token Index: 608

Text #12

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0805. Min Act: -0.0000

Data Index: 858126 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0883. Min Act: -0.0000

Data Index: 1042529 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0842. Min Act: -0.0000

Data Index: 501703 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0847. Min Act: -0.0000

Data Index: 1428650 (Python Code)

Max Activating Token Index: 178

Text #16

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0811. Min Act: -0.0000

Data Index: 1018198 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0857. Min Act: -0.0000

Data Index: 368885 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0813. Min Act: -0.0000

Data Index: 1551388 (Python Code)

Max Activating Token Index: 69

Text #19

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0803. Min Act: -0.0000

Data Index: 334461 (C4 (Web Text))

Max Activating Token Index: 582