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

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

Neuron 4739 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3250. Min Range: -0.3250

Max Act: 0.3074. Min Act: -0.0001

Data Index: 642556 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 0.3250. Min Range: -0.3250

Max Act: 0.3134. Min Act: -0.0001

Data Index: 411811 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 0.3250. Min Range: -0.3250

Max Act: 0.3176. Min Act: -0.0001

Data Index: 89238 (C4 (Web Text))

Max Activating Token Index: 329

Text #3

Max Range: 0.3250. Min Range: -0.3250

Max Act: 0.3250. Min Act: -0.0001

Data Index: 69039 (C4 (Web Text))

Max Activating Token Index: 228

Text #4

Max Range: 0.3250. Min Range: -0.3250

Max Act: 0.3219. Min Act: -0.0001

Data Index: 642418 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 0.3250. Min Range: -0.3250

Max Act: 0.2959. Min Act: -0.0001

Data Index: 365395 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 0.3250. Min Range: -0.3250

Max Act: 0.2890. Min Act: -0.0001

Data Index: 233590 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 0.3250. Min Range: -0.3250

Max Act: 0.2823. Min Act: -0.0001

Data Index: 694954 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 0.3250. Min Range: -0.3250

Max Act: 0.2855. Min Act: -0.0001

Data Index: 762566 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 0.3250. Min Range: -0.3250

Max Act: 0.2941. Min Act: -0.0001

Data Index: 1184893 (C4 (Web Text))

Max Activating Token Index: 361

Text #10

Max Range: 0.3250. Min Range: -0.3250

Max Act: 0.2826. Min Act: -0.0001

Data Index: 565569 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 0.3250. Min Range: -0.3250

Max Act: 0.2936. Min Act: -0.0001

Data Index: 232683 (C4 (Web Text))

Max Activating Token Index: 433

Text #12

Max Range: 0.3250. Min Range: -0.3250

Max Act: 0.2696. Min Act: -0.0001

Data Index: 239872 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 0.3250. Min Range: -0.3250

Max Act: 0.2848. Min Act: -0.0001

Data Index: 975574 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 0.3250. Min Range: -0.3250

Max Act: 0.2739. Min Act: -0.0001

Data Index: 935181 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 0.3250. Min Range: -0.3250

Max Act: 0.2822. Min Act: -0.0001

Data Index: 602009 (C4 (Web Text))

Max Activating Token Index: 258

Text #16

Max Range: 0.3250. Min Range: -0.3250

Max Act: 0.2840. Min Act: -0.0001

Data Index: 130258 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 0.3250. Min Range: -0.3250

Max Act: 0.2683. Min Act: -0.0001

Data Index: 666117 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 0.3250. Min Range: -0.3250

Max Act: 0.2898. Min Act: -0.0001

Data Index: 641852 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 0.3250. Min Range: -0.3250

Max Act: 0.2556. Min Act: -0.0001

Data Index: 73612 (C4 (Web Text))

Max Activating Token Index: 180