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

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

Neuron 117 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0383. Min Range: -1.0383

Max Act: 1.0383. Min Act: -0.0001

Data Index: 618340 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.9921. Min Act: -0.0002

Data Index: 465902 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.8981. Min Act: -0.0002

Data Index: 685950 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.9278. Min Act: -0.0002

Data Index: 506676 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.7648. Min Act: -0.0002

Data Index: 511035 (C4 (Web Text))

Max Activating Token Index: 898

Text #5

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.9546. Min Act: -0.0002

Data Index: 1290212 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.9144. Min Act: -0.0002

Data Index: 1241272 (C4 (Web Text))

Max Activating Token Index: 950

Text #7

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.9186. Min Act: -0.0002

Data Index: 1260336 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.8230. Min Act: -0.0002

Data Index: 38874 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.8859. Min Act: -0.0001

Data Index: 47773 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.7585. Min Act: -0.0002

Data Index: 1348708 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.8443. Min Act: -0.0001

Data Index: 14249 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.7029. Min Act: -0.0002

Data Index: 781314 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.8999. Min Act: -0.0001

Data Index: 411257 (C4 (Web Text))

Max Activating Token Index: 359

Text #14

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.8021. Min Act: -0.0001

Data Index: 1260915 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.8800. Min Act: -0.0001

Data Index: 1126684 (C4 (Web Text))

Max Activating Token Index: 370

Text #16

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.7085. Min Act: -0.0001

Data Index: 1109872 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.8501. Min Act: -0.0001

Data Index: 645652 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.7863. Min Act: -0.0001

Data Index: 944315 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.8329. Min Act: -0.0002

Data Index: 895258 (C4 (Web Text))

Max Activating Token Index: 225