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

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

Neuron 1350 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1143. Min Act: -0.0001

Data Index: 600334 (C4 (Web Text))

Max Activating Token Index: 603

Text #1

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1182. Min Act: -0.0001

Data Index: 624811 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1040. Min Act: -0.0001

Data Index: 686691 (C4 (Web Text))

Max Activating Token Index: 472

Text #3

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1083. Min Act: -0.0001

Data Index: 1067792 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1202. Min Act: -0.0001

Data Index: 331726 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0962. Min Act: -0.0001

Data Index: 143994 (C4 (Web Text))

Max Activating Token Index: 990

Text #6

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1027. Min Act: -0.0001

Data Index: 801652 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0983. Min Act: -0.0001

Data Index: 729590 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0972. Min Act: -0.0001

Data Index: 99969 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0989. Min Act: -0.0001

Data Index: 710131 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0944. Min Act: -0.0001

Data Index: 1287585 (C4 (Web Text))

Max Activating Token Index: 189

Text #11

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0899. Min Act: -0.0001

Data Index: 1022561 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0910. Min Act: -0.0001

Data Index: 553035 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0929. Min Act: -0.0001

Data Index: 184413 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0926. Min Act: -0.0001

Data Index: 1121308 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0924. Min Act: -0.0001

Data Index: 242454 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0918. Min Act: -0.0001

Data Index: 1331093 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0916. Min Act: -0.0001

Data Index: 691265 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0830. Min Act: -0.0001

Data Index: 789248 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0858. Min Act: -0.0001

Data Index: 164406 (C4 (Web Text))

Max Activating Token Index: 188