Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 889 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1222. Min Act: -0.0002

Data Index: 1047711 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1150. Min Act: -0.0002

Data Index: 480270 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1108. Min Act: -0.0002

Data Index: 58432 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1096. Min Act: -0.0002

Data Index: 588612 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1049. Min Act: -0.0002

Data Index: 878560 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1043. Min Act: -0.0002

Data Index: 387766 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1060. Min Act: -0.0001

Data Index: 469444 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1071. Min Act: -0.0002

Data Index: 456689 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1055. Min Act: -0.0001

Data Index: 255442 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1016. Min Act: -0.0002

Data Index: 1204541 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1038. Min Act: -0.0002

Data Index: 121276 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1012. Min Act: -0.0001

Data Index: 84519 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0982. Min Act: -0.0001

Data Index: 1318964 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1003. Min Act: -0.0001

Data Index: 489890 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0974. Min Act: -0.0002

Data Index: 1534331 (Python Code)

Max Activating Token Index: 353

Text #15

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0976. Min Act: -0.0002

Data Index: 1458335 (Python Code)

Max Activating Token Index: 71

Text #16

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0976. Min Act: -0.0002

Data Index: 1630272 (Python Code)

Max Activating Token Index: 738

Text #17

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0981. Min Act: -0.0001

Data Index: 167450 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0961. Min Act: -0.0002

Data Index: 1383656 (Python Code)

Max Activating Token Index: 879

Text #19

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0988. Min Act: -0.0002

Data Index: 1616960 (Python Code)

Max Activating Token Index: 388