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

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

Neuron 3775 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2746. Min Range: -3.2746

Max Act: 3.2746. Min Act: -0.0001

Data Index: 1107984 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 3.2746. Min Range: -3.2746

Max Act: 3.0687. Min Act: -0.0001

Data Index: 1158733 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 3.2746. Min Range: -3.2746

Max Act: 2.7570. Min Act: -0.0000

Data Index: 978757 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 3.2746. Min Range: -3.2746

Max Act: 2.7860. Min Act: -0.0001

Data Index: 1189164 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 3.2746. Min Range: -3.2746

Max Act: 2.8840. Min Act: -0.0001

Data Index: 455787 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 3.2746. Min Range: -3.2746

Max Act: 2.8157. Min Act: -0.0000

Data Index: 1034287 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 3.2746. Min Range: -3.2746

Max Act: 2.9422. Min Act: -0.0000

Data Index: 951744 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 3.2746. Min Range: -3.2746

Max Act: 2.6669. Min Act: -0.0000

Data Index: 695583 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 3.2746. Min Range: -3.2746

Max Act: 2.7716. Min Act: -0.0000

Data Index: 343215 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 3.2746. Min Range: -3.2746

Max Act: 2.7160. Min Act: -0.0000

Data Index: 988328 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 3.2746. Min Range: -3.2746

Max Act: 2.8067. Min Act: -0.0001

Data Index: 1281098 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 3.2746. Min Range: -3.2746

Max Act: 2.6309. Min Act: -0.0000

Data Index: 1067012 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 3.2746. Min Range: -3.2746

Max Act: 2.6741. Min Act: -0.0001

Data Index: 209679 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 3.2746. Min Range: -3.2746

Max Act: 2.5835. Min Act: -0.0000

Data Index: 509347 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 3.2746. Min Range: -3.2746

Max Act: 2.5789. Min Act: -0.0000

Data Index: 711095 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 3.2746. Min Range: -3.2746

Max Act: 2.5633. Min Act: -0.0000

Data Index: 76625 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 3.2746. Min Range: -3.2746

Max Act: 2.5291. Min Act: -0.0000

Data Index: 464501 (C4 (Web Text))

Max Activating Token Index: 709

Text #17

Max Range: 3.2746. Min Range: -3.2746

Max Act: 2.3950. Min Act: -0.0000

Data Index: 267505 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 3.2746. Min Range: -3.2746

Max Act: 2.2898. Min Act: -0.0001

Data Index: 757592 (C4 (Web Text))

Max Activating Token Index: 272

Text #19

Max Range: 3.2746. Min Range: -3.2746

Max Act: 2.6007. Min Act: -0.0001

Data Index: 29809 (C4 (Web Text))

Max Activating Token Index: 134