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

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

Neuron 1038 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: 0.1053. Min Range: -0.1053

Max Act: 0.1043. Min Act: -0.0002

Data Index: 311825 (C4 (Web Text))

Max Activating Token Index: 501

Text #1

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.1053. Min Act: -0.0002

Data Index: 648540 (C4 (Web Text))

Max Activating Token Index: 593

Text #2

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.1041. Min Act: -0.0002

Data Index: 20893 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.1043. Min Act: -0.0002

Data Index: 687577 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.1009. Min Act: -0.0002

Data Index: 69260 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.1025. Min Act: -0.0002

Data Index: 636551 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0984. Min Act: -0.0002

Data Index: 593823 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0992. Min Act: -0.0002

Data Index: 133901 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.1005. Min Act: -0.0002

Data Index: 441211 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0997. Min Act: -0.0002

Data Index: 342454 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0969. Min Act: -0.0002

Data Index: 515509 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0985. Min Act: -0.0002

Data Index: 269675 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0955. Min Act: -0.0002

Data Index: 149062 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0981. Min Act: -0.0002

Data Index: 103868 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0908. Min Act: -0.0002

Data Index: 684589 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0945. Min Act: -0.0002

Data Index: 1220158 (C4 (Web Text))

Max Activating Token Index: 380

Text #16

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0966. Min Act: -0.0002

Data Index: 929012 (C4 (Web Text))

Max Activating Token Index: 585

Text #17

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0960. Min Act: -0.0002

Data Index: 1648389 (Python Code)

Max Activating Token Index: 964

Text #18

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0943. Min Act: -0.0002

Data Index: 317800 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0948. Min Act: -0.0002

Data Index: 1163186 (C4 (Web Text))

Max Activating Token Index: 577