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

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

Neuron 4952 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.1102. Min Act: -0.0000

Data Index: 1109521 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.1030. Min Act: -0.0000

Data Index: 969121 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.1002. Min Act: -0.0000

Data Index: 129657 (C4 (Web Text))

Max Activating Token Index: 639

Text #3

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0973. Min Act: -0.0000

Data Index: 458298 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0955. Min Act: -0.0000

Data Index: 827541 (C4 (Web Text))

Max Activating Token Index: 448

Text #5

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0893. Min Act: -0.0000

Data Index: 1047011 (C4 (Web Text))

Max Activating Token Index: 260

Text #6

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0852. Min Act: -0.0000

Data Index: 323763 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0919. Min Act: -0.0000

Data Index: 28247 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0868. Min Act: -0.0000

Data Index: 719880 (C4 (Web Text))

Max Activating Token Index: 579

Text #9

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0846. Min Act: -0.0000

Data Index: 540531 (C4 (Web Text))

Max Activating Token Index: 621

Text #10

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0833. Min Act: -0.0000

Data Index: 940657 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0828. Min Act: -0.0000

Data Index: 762460 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0821. Min Act: -0.0000

Data Index: 560882 (C4 (Web Text))

Max Activating Token Index: 537

Text #13

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0767. Min Act: -0.0000

Data Index: 667140 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0776. Min Act: -0.0000

Data Index: 85861 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0654. Min Act: -0.0000

Data Index: 849170 (C4 (Web Text))

Max Activating Token Index: 633

Text #16

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0725. Min Act: -0.0000

Data Index: 57017 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0711. Min Act: -0.0000

Data Index: 681953 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0713. Min Act: -0.0000

Data Index: 454521 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0693. Min Act: -0.0000

Data Index: 635403 (C4 (Web Text))

Max Activating Token Index: 800