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

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

Neuron 1295 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1457. Min Act: -0.0000

Data Index: 71504 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1258. Min Act: -0.0000

Data Index: 559318 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1205. Min Act: -0.0000

Data Index: 1318839 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1151. Min Act: -0.0000

Data Index: 585506 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1150. Min Act: -0.0000

Data Index: 735601 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1148. Min Act: -0.0001

Data Index: 856980 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1089. Min Act: -0.0001

Data Index: 1503511 (Python Code)

Max Activating Token Index: 749

Text #7

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1081. Min Act: -0.0001

Data Index: 1616128 (Python Code)

Max Activating Token Index: 790

Text #8

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1210. Min Act: -0.0000

Data Index: 1322736 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1072. Min Act: -0.0000

Data Index: 1083700 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1054. Min Act: -0.0001

Data Index: 1481535 (Python Code)

Max Activating Token Index: 647

Text #11

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1084. Min Act: -0.0001

Data Index: 796233 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1038. Min Act: -0.0001

Data Index: 1211553 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1069. Min Act: -0.0001

Data Index: 714267 (C4 (Web Text))

Max Activating Token Index: 803

Text #14

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1011. Min Act: -0.0000

Data Index: 1199012 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1101. Min Act: -0.0000

Data Index: 132814 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1056. Min Act: -0.0000

Data Index: 758440 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.0937. Min Act: -0.0001

Data Index: 1457187 (Python Code)

Max Activating Token Index: 730

Text #18

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1045. Min Act: -0.0001

Data Index: 1542522 (Python Code)

Max Activating Token Index: 240

Text #19

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.0985. Min Act: -0.0001

Data Index: 102644 (C4 (Web Text))

Max Activating Token Index: 174