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

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

Neuron 2228 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1264. Min Act: -0.0002

Data Index: 325613 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1250. Min Act: -0.0001

Data Index: 584868 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1103. Min Act: -0.0001

Data Index: 1141485 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0998. Min Act: -0.0001

Data Index: 446876 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1011. Min Act: -0.0002

Data Index: 667811 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1105. Min Act: -0.0002

Data Index: 1352944 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0990. Min Act: -0.0002

Data Index: 453819 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0980. Min Act: -0.0002

Data Index: 626400 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1004. Min Act: -0.0002

Data Index: 290494 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1005. Min Act: -0.0001

Data Index: 1136864 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0928. Min Act: -0.0001

Data Index: 1339559 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0986. Min Act: -0.0001

Data Index: 167239 (C4 (Web Text))

Max Activating Token Index: 3

Text #12

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1026. Min Act: -0.0002

Data Index: 1076541 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0988. Min Act: -0.0001

Data Index: 1147072 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1049. Min Act: -0.0001

Data Index: 483129 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0957. Min Act: -0.0002

Data Index: 865916 (C4 (Web Text))

Max Activating Token Index: 972

Text #16

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0954. Min Act: -0.0001

Data Index: 817580 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0982. Min Act: -0.0001

Data Index: 709219 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0946. Min Act: -0.0002

Data Index: 1349286 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0940. Min Act: -0.0002

Data Index: 256688 (C4 (Web Text))

Max Activating Token Index: 942