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

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

Neuron 3638 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.4012. Min Act: -0.0000

Data Index: 632459 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.3039. Min Act: -0.0000

Data Index: 743930 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.3245. Min Act: -0.0000

Data Index: 317413 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.3311. Min Act: -0.0000

Data Index: 945765 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.3279. Min Act: -0.0000

Data Index: 85299 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2997. Min Act: -0.0000

Data Index: 570103 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2964. Min Act: -0.0000

Data Index: 1246789 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.3029. Min Act: -0.0000

Data Index: 837059 (C4 (Web Text))

Max Activating Token Index: 865

Text #8

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.3042. Min Act: -0.0000

Data Index: 98336 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.3073. Min Act: -0.0000

Data Index: 1092790 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2742. Min Act: -0.0000

Data Index: 1043925 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2525. Min Act: -0.0000

Data Index: 365494 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.3015. Min Act: -0.0000

Data Index: 15284 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2993. Min Act: -0.0000

Data Index: 507948 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2853. Min Act: -0.0000

Data Index: 267017 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2745. Min Act: -0.0000

Data Index: 235450 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.3063. Min Act: -0.0000

Data Index: 164941 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2796. Min Act: -0.0000

Data Index: 577717 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2703. Min Act: -0.0000

Data Index: 144911 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2906. Min Act: -0.0000

Data Index: 1100473 (C4 (Web Text))

Max Activating Token Index: 465