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

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

Neuron 4358 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.4927. Min Act: -0.0001

Data Index: 810721 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.4599. Min Act: -0.0001

Data Index: 677810 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.4051. Min Act: -0.0001

Data Index: 997130 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3905. Min Act: -0.0001

Data Index: 1141025 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3599. Min Act: -0.0001

Data Index: 245420 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.4221. Min Act: -0.0001

Data Index: 1313836 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.4000. Min Act: -0.0001

Data Index: 1320209 (C4 (Web Text))

Max Activating Token Index: 470

Text #7

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.4013. Min Act: -0.0001

Data Index: 1156967 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3850. Min Act: -0.0001

Data Index: 522840 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3979. Min Act: -0.0001

Data Index: 315612 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3337. Min Act: -0.0001

Data Index: 705844 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3457. Min Act: -0.0001

Data Index: 532969 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3519. Min Act: -0.0001

Data Index: 710590 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3551. Min Act: -0.0001

Data Index: 511135 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3890. Min Act: -0.0001

Data Index: 999892 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3508. Min Act: -0.0001

Data Index: 352163 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3791. Min Act: -0.0001

Data Index: 234918 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3365. Min Act: -0.0001

Data Index: 1188243 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3410. Min Act: -0.0001

Data Index: 34541 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3384. Min Act: -0.0001

Data Index: 48068 (C4 (Web Text))

Max Activating Token Index: 527