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

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

Neuron 3721 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0697. Min Act: -0.0002

Data Index: 835731 (C4 (Web Text))

Max Activating Token Index: 822

Text #1

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0708. Min Act: -0.0002

Data Index: 682406 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0650. Min Act: -0.0002

Data Index: 881976 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0632. Min Act: -0.0001

Data Index: 1040396 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0625. Min Act: -0.0001

Data Index: 47244 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0609. Min Act: -0.0001

Data Index: 1117782 (C4 (Web Text))

Max Activating Token Index: 485

Text #6

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0607. Min Act: -0.0001

Data Index: 711791 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0614. Min Act: -0.0001

Data Index: 479616 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0595. Min Act: -0.0001

Data Index: 1196811 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0617. Min Act: -0.0001

Data Index: 85457 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0568. Min Act: -0.0001

Data Index: 370507 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0584. Min Act: -0.0001

Data Index: 814872 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0596. Min Act: -0.0001

Data Index: 1043512 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0545. Min Act: -0.0001

Data Index: 994477 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0574. Min Act: -0.0002

Data Index: 70515 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0594. Min Act: -0.0001

Data Index: 778899 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0572. Min Act: -0.0002

Data Index: 983527 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0571. Min Act: -0.0002

Data Index: 748727 (C4 (Web Text))

Max Activating Token Index: 954

Text #18

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0569. Min Act: -0.0002

Data Index: 221100 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0545. Min Act: -0.0002

Data Index: 1346368 (C4 (Web Text))

Max Activating Token Index: 991