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

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

Neuron 4272 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1562. Min Act: -0.0001

Data Index: 389625 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1343. Min Act: -0.0000

Data Index: 216728 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1198. Min Act: -0.0001

Data Index: 1102441 (C4 (Web Text))

Max Activating Token Index: 217

Text #3

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1303. Min Act: -0.0001

Data Index: 427443 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1088. Min Act: -0.0001

Data Index: 758124 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1126. Min Act: -0.0001

Data Index: 404273 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1123. Min Act: -0.0001

Data Index: 554887 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1186. Min Act: -0.0000

Data Index: 714485 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1114. Min Act: -0.0000

Data Index: 185847 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1169. Min Act: -0.0001

Data Index: 836445 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1012. Min Act: -0.0000

Data Index: 931938 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1093. Min Act: -0.0001

Data Index: 152013 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1045. Min Act: -0.0001

Data Index: 283802 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1012. Min Act: -0.0001

Data Index: 930770 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1033. Min Act: -0.0000

Data Index: 16180 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.0967. Min Act: -0.0001

Data Index: 735377 (C4 (Web Text))

Max Activating Token Index: 178

Text #16

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1066. Min Act: -0.0001

Data Index: 569341 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1028. Min Act: -0.0001

Data Index: 173096 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1026. Min Act: -0.0000

Data Index: 1002245 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.0951. Min Act: -0.0001

Data Index: 539083 (C4 (Web Text))

Max Activating Token Index: 213