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

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

Neuron 68 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1647. Min Act: -0.0001

Data Index: 1273878 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1283. Min Act: -0.0001

Data Index: 58979 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1102. Min Act: -0.0001

Data Index: 318875 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1087. Min Act: -0.0001

Data Index: 1138133 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1048. Min Act: -0.0001

Data Index: 1157261 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1026. Min Act: -0.0001

Data Index: 560382 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1011. Min Act: -0.0001

Data Index: 650371 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1009. Min Act: -0.0001

Data Index: 256822 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1042. Min Act: -0.0001

Data Index: 1218928 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1010. Min Act: -0.0001

Data Index: 33636 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.0999. Min Act: -0.0001

Data Index: 918907 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.0932. Min Act: -0.0001

Data Index: 1144153 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.0944. Min Act: -0.0001

Data Index: 912056 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.0931. Min Act: -0.0001

Data Index: 843611 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.0945. Min Act: -0.0001

Data Index: 600934 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.0862. Min Act: -0.0001

Data Index: 902531 (C4 (Web Text))

Max Activating Token Index: 897

Text #16

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.0914. Min Act: -0.0001

Data Index: 959971 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.0906. Min Act: -0.0001

Data Index: 121031 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.0894. Min Act: -0.0001

Data Index: 590787 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.0891. Min Act: -0.0001

Data Index: 917123 (C4 (Web Text))

Max Activating Token Index: 952