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

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

Neuron 790 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0063. Min Act: -0.0003

Data Index: 236628 (C4 (Web Text))

Max Activating Token Index: 399

Text #1

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0053. Min Act: -0.0003

Data Index: 1128497 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0053. Min Act: -0.0003

Data Index: 638787 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0055. Min Act: -0.0003

Data Index: 924433 (C4 (Web Text))

Max Activating Token Index: 890

Text #4

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0052. Min Act: -0.0003

Data Index: 246447 (C4 (Web Text))

Max Activating Token Index: 404

Text #5

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0048. Min Act: -0.0003

Data Index: 347124 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0050. Min Act: -0.0003

Data Index: 197428 (C4 (Web Text))

Max Activating Token Index: 352

Text #7

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0052. Min Act: -0.0003

Data Index: 1068710 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0046. Min Act: -0.0003

Data Index: 502612 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0048. Min Act: -0.0003

Data Index: 553360 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0048. Min Act: -0.0003

Data Index: 59775 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0046. Min Act: -0.0003

Data Index: 1259216 (C4 (Web Text))

Max Activating Token Index: 758

Text #12

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0048. Min Act: -0.0003

Data Index: 951043 (C4 (Web Text))

Max Activating Token Index: 187

Text #13

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0049. Min Act: -0.0003

Data Index: 293983 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0045. Min Act: -0.0003

Data Index: 1131136 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0050. Min Act: -0.0003

Data Index: 1196340 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0047. Min Act: -0.0003

Data Index: 1338453 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0042. Min Act: -0.0003

Data Index: 253674 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0047. Min Act: -0.0003

Data Index: 662133 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0047. Min Act: -0.0003

Data Index: 681976 (C4 (Web Text))

Max Activating Token Index: 849