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

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

Neuron 2415 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: 0.1195. Min Range: -0.1195

Max Act: 0.1195. Min Act: -0.0001

Data Index: 897471 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1126. Min Act: -0.0001

Data Index: 564299 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1111. Min Act: -0.0001

Data Index: 1071 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1054. Min Act: -0.0001

Data Index: 1355977 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1043. Min Act: 0.0000

Data Index: 500258 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1004. Min Act: -0.0001

Data Index: 45282 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0982. Min Act: -0.0000

Data Index: 88347 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0918. Min Act: -0.0001

Data Index: 505880 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0978. Min Act: -0.0001

Data Index: 825708 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0967. Min Act: -0.0000

Data Index: 95702 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0947. Min Act: -0.0001

Data Index: 1248725 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0900. Min Act: -0.0001

Data Index: 380358 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0927. Min Act: 0.0001

Data Index: 1334719 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0931. Min Act: -0.0000

Data Index: 238644 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0923. Min Act: -0.0001

Data Index: 1104127 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0880. Min Act: -0.0001

Data Index: 1343550 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0908. Min Act: 0.0001

Data Index: 526645 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0877. Min Act: -0.0001

Data Index: 1094287 (C4 (Web Text))

Max Activating Token Index: 965

Text #18

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0904. Min Act: -0.0001

Data Index: 942321 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0904. Min Act: -0.0001

Data Index: 1170979 (C4 (Web Text))

Max Activating Token Index: 370