Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2332 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7063. Min Range: -0.7063

Max Act: 0.7063. Min Act: -0.0000

Data Index: 1283895 (C4 (Web Text))

Max Activating Token Index: 696

Text #1

Max Range: 0.7063. Min Range: -0.7063

Max Act: 0.5991. Min Act: -0.0000

Data Index: 1202186 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 0.7063. Min Range: -0.7063

Max Act: 0.6802. Min Act: -0.0000

Data Index: 1202883 (C4 (Web Text))

Max Activating Token Index: 823

Text #3

Max Range: 0.7063. Min Range: -0.7063

Max Act: 0.6012. Min Act: -0.0000

Data Index: 954687 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 0.7063. Min Range: -0.7063

Max Act: 0.6048. Min Act: -0.0000

Data Index: 657574 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 0.7063. Min Range: -0.7063

Max Act: 0.6156. Min Act: -0.0000

Data Index: 560375 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 0.7063. Min Range: -0.7063

Max Act: 0.5850. Min Act: -0.0000

Data Index: 1127595 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 0.7063. Min Range: -0.7063

Max Act: 0.5488. Min Act: -0.0000

Data Index: 55885 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 0.7063. Min Range: -0.7063

Max Act: 0.5664. Min Act: -0.0000

Data Index: 67059 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 0.7063. Min Range: -0.7063

Max Act: 0.5549. Min Act: -0.0000

Data Index: 1169270 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 0.7063. Min Range: -0.7063

Max Act: 0.5740. Min Act: -0.0000

Data Index: 1338730 (C4 (Web Text))

Max Activating Token Index: 397

Text #11

Max Range: 0.7063. Min Range: -0.7063

Max Act: 0.5818. Min Act: -0.0000

Data Index: 1505014 (Python Code)

Max Activating Token Index: 928

Text #12

Max Range: 0.7063. Min Range: -0.7063

Max Act: 0.5591. Min Act: -0.0000

Data Index: 1129980 (C4 (Web Text))

Max Activating Token Index: 958

Text #13

Max Range: 0.7063. Min Range: -0.7063

Max Act: 0.5624. Min Act: -0.0000

Data Index: 709594 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 0.7063. Min Range: -0.7063

Max Act: 0.5607. Min Act: -0.0000

Data Index: 424870 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 0.7063. Min Range: -0.7063

Max Act: 0.5863. Min Act: -0.0000

Data Index: 916187 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 0.7063. Min Range: -0.7063

Max Act: 0.5498. Min Act: -0.0000

Data Index: 839726 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 0.7063. Min Range: -0.7063

Max Act: 0.5353. Min Act: -0.0000

Data Index: 767992 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 0.7063. Min Range: -0.7063

Max Act: 0.5372. Min Act: -0.0000

Data Index: 998489 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 0.7063. Min Range: -0.7063

Max Act: 0.5547. Min Act: -0.0000

Data Index: 65240 (C4 (Web Text))

Max Activating Token Index: 947