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

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

Neuron 3055 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.1108. Min Act: -0.0001

Data Index: 1045802 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.1117. Min Act: -0.0001

Data Index: 23162 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.1108. Min Act: -0.0001

Data Index: 1040240 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.1118. Min Act: -0.0001

Data Index: 101357 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.1107. Min Act: -0.0001

Data Index: 26070 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.1034. Min Act: -0.0001

Data Index: 1238324 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.1011. Min Act: -0.0001

Data Index: 47672 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.1071. Min Act: -0.0001

Data Index: 433456 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.1024. Min Act: -0.0001

Data Index: 825463 (C4 (Web Text))

Max Activating Token Index: 247

Text #9

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0954. Min Act: -0.0001

Data Index: 441852 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0978. Min Act: -0.0001

Data Index: 1383905 (Python Code)

Max Activating Token Index: 160

Text #11

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0938. Min Act: -0.0001

Data Index: 641494 (C4 (Web Text))

Max Activating Token Index: 251

Text #12

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0895. Min Act: -0.0001

Data Index: 856512 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0824. Min Act: -0.0001

Data Index: 151695 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0871. Min Act: -0.0001

Data Index: 730508 (C4 (Web Text))

Max Activating Token Index: 511

Text #15

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0815. Min Act: -0.0001

Data Index: 1261646 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0832. Min Act: -0.0001

Data Index: 703383 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0796. Min Act: -0.0001

Data Index: 1239791 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0850. Min Act: -0.0001

Data Index: 772213 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0815. Min Act: -0.0001

Data Index: 367668 (C4 (Web Text))

Max Activating Token Index: 829