Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4318 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0051. Min Act: -0.0002

Data Index: 926434 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0033. Min Act: -0.0002

Data Index: 848090 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0041. Min Act: -0.0002

Data Index: 688471 (C4 (Web Text))

Max Activating Token Index: 767

Text #3

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0036. Min Act: -0.0002

Data Index: 832246 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0037. Min Act: -0.0002

Data Index: 1112808 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0036. Min Act: -0.0002

Data Index: 1307225 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0032. Min Act: -0.0002

Data Index: 1187767 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0035. Min Act: -0.0002

Data Index: 159123 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0035. Min Act: -0.0002

Data Index: 1064266 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0035. Min Act: -0.0002

Data Index: 542758 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0034. Min Act: -0.0002

Data Index: 62449 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0036. Min Act: -0.0002

Data Index: 997915 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0036. Min Act: -0.0002

Data Index: 1132956 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0034. Min Act: -0.0002

Data Index: 595790 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0032. Min Act: -0.0002

Data Index: 1166370 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0034. Min Act: -0.0002

Data Index: 149049 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0031. Min Act: -0.0002

Data Index: 284512 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0033. Min Act: -0.0002

Data Index: 550875 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0033. Min Act: -0.0002

Data Index: 792434 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0032. Min Act: -0.0002

Data Index: 92935 (C4 (Web Text))

Max Activating Token Index: 269