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

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

Neuron 1421 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.1563. Min Act: -0.0001

Data Index: 1197076 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.0330. Min Act: -0.0001

Data Index: 1271205 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.0566. Min Act: -0.0001

Data Index: 606557 (C4 (Web Text))

Max Activating Token Index: 887

Text #3

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9901. Min Act: -0.0001

Data Index: 366929 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9930. Min Act: -0.0001

Data Index: 1265904 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9753. Min Act: -0.0001

Data Index: 947973 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9764. Min Act: -0.0001

Data Index: 303243 (C4 (Web Text))

Max Activating Token Index: 973

Text #7

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9791. Min Act: -0.0001

Data Index: 1097838 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.0061. Min Act: -0.0001

Data Index: 1190707 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9125. Min Act: -0.0001

Data Index: 213082 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9601. Min Act: -0.0001

Data Index: 673562 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9710. Min Act: -0.0001

Data Index: 173833 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9546. Min Act: -0.0001

Data Index: 454606 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.8678. Min Act: -0.0001

Data Index: 993200 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9292. Min Act: -0.0001

Data Index: 1209315 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.8746. Min Act: -0.0001

Data Index: 1152204 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9064. Min Act: -0.0001

Data Index: 764345 (C4 (Web Text))

Max Activating Token Index: 450

Text #17

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.8743. Min Act: -0.0001

Data Index: 567001 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9327. Min Act: -0.0001

Data Index: 373187 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.8882. Min Act: -0.0001

Data Index: 79165 (C4 (Web Text))

Max Activating Token Index: 664