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

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

Neuron 4916 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: 0.1118. Min Range: -0.1118

Max Act: 0.0717. Min Act: -0.0002

Data Index: 1220281 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.1118. Min Act: -0.0002

Data Index: 584749 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0957. Min Act: -0.0002

Data Index: 806165 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0848. Min Act: -0.0002

Data Index: 237902 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0769. Min Act: -0.0002

Data Index: 1128833 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.1011. Min Act: -0.0002

Data Index: 1146363 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0726. Min Act: -0.0002

Data Index: 1161028 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0555. Min Act: -0.0002

Data Index: 676467 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0644. Min Act: -0.0002

Data Index: 1513750 (Python Code)

Max Activating Token Index: 278

Text #9

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.1058. Min Act: -0.0002

Data Index: 932792 (C4 (Web Text))

Max Activating Token Index: 420

Text #10

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0806. Min Act: -0.0002

Data Index: 241721 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0481. Min Act: -0.0002

Data Index: 793111 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0867. Min Act: -0.0002

Data Index: 832053 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0629. Min Act: -0.0002

Data Index: 1339910 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0613. Min Act: -0.0002

Data Index: 283610 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0785. Min Act: -0.0002

Data Index: 516862 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0531. Min Act: -0.0002

Data Index: 677754 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0737. Min Act: -0.0002

Data Index: 280964 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0812. Min Act: -0.0002

Data Index: 807510 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0727. Min Act: -0.0002

Data Index: 1300931 (C4 (Web Text))

Max Activating Token Index: 45