Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1788 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.1209. Min Act: -0.0003

Data Index: 246719 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.1106. Min Act: -0.0003

Data Index: 217159 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.1061. Min Act: -0.0003

Data Index: 268221 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.1034. Min Act: -0.0003

Data Index: 2518 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.0995. Min Act: -0.0003

Data Index: 165264 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.1008. Min Act: -0.0003

Data Index: 1170469 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.0995. Min Act: -0.0003

Data Index: 429066 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.0947. Min Act: -0.0003

Data Index: 807941 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.0975. Min Act: -0.0003

Data Index: 96270 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.0930. Min Act: -0.0003

Data Index: 1026070 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.0946. Min Act: -0.0003

Data Index: 985788 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.0920. Min Act: -0.0003

Data Index: 146637 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.0900. Min Act: -0.0003

Data Index: 434478 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.0878. Min Act: -0.0003

Data Index: 875147 (C4 (Web Text))

Max Activating Token Index: 619

Text #14

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.0891. Min Act: -0.0003

Data Index: 611057 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.0877. Min Act: -0.0003

Data Index: 369200 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.0847. Min Act: -0.0003

Data Index: 843002 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.0887. Min Act: -0.0003

Data Index: 506650 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.0837. Min Act: -0.0003

Data Index: 1225823 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.0844. Min Act: -0.0003

Data Index: 814715 (C4 (Web Text))

Max Activating Token Index: 205