Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 175 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.1474. Min Range: -1.1474

Max Act: 1.1474. Min Act: -0.0001

Data Index: 93696 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 1.1474. Min Range: -1.1474

Max Act: 0.9015. Min Act: -0.0001

Data Index: 707712 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 1.1474. Min Range: -1.1474

Max Act: 0.8864. Min Act: -0.0001

Data Index: 700642 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 1.1474. Min Range: -1.1474

Max Act: 0.9961. Min Act: -0.0001

Data Index: 715874 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 1.1474. Min Range: -1.1474

Max Act: 0.9127. Min Act: -0.0001

Data Index: 870719 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 1.1474. Min Range: -1.1474

Max Act: 0.9092. Min Act: -0.0001

Data Index: 1099161 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 1.1474. Min Range: -1.1474

Max Act: 0.7479. Min Act: -0.0001

Data Index: 1343379 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 1.1474. Min Range: -1.1474

Max Act: 0.8037. Min Act: -0.0001

Data Index: 931620 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 1.1474. Min Range: -1.1474

Max Act: 0.8449. Min Act: -0.0001

Data Index: 499548 (C4 (Web Text))

Max Activating Token Index: 867

Text #9

Max Range: 1.1474. Min Range: -1.1474

Max Act: 0.8383. Min Act: -0.0001

Data Index: 913706 (C4 (Web Text))

Max Activating Token Index: 589

Text #10

Max Range: 1.1474. Min Range: -1.1474

Max Act: 0.8401. Min Act: -0.0001

Data Index: 488124 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 1.1474. Min Range: -1.1474

Max Act: 0.8021. Min Act: -0.0001

Data Index: 665217 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 1.1474. Min Range: -1.1474

Max Act: 0.8158. Min Act: -0.0001

Data Index: 480879 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 1.1474. Min Range: -1.1474

Max Act: 0.7631. Min Act: -0.0001

Data Index: 1140534 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 1.1474. Min Range: -1.1474

Max Act: 0.8086. Min Act: -0.0001

Data Index: 608862 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 1.1474. Min Range: -1.1474

Max Act: 0.8180. Min Act: -0.0001

Data Index: 910736 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 1.1474. Min Range: -1.1474

Max Act: 0.7899. Min Act: -0.0001

Data Index: 360693 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 1.1474. Min Range: -1.1474

Max Act: 0.8082. Min Act: -0.0001

Data Index: 1012050 (C4 (Web Text))

Max Activating Token Index: 70

Text #18

Max Range: 1.1474. Min Range: -1.1474

Max Act: 0.8022. Min Act: -0.0001

Data Index: 101013 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 1.1474. Min Range: -1.1474

Max Act: 0.7769. Min Act: -0.0001

Data Index: 151791 (C4 (Web Text))

Max Activating Token Index: 38