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

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

Neuron 2399 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.7473. Min Act: -0.0000

Data Index: 936479 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.7689. Min Act: -0.0000

Data Index: 537772 (C4 (Web Text))

Max Activating Token Index: 600

Text #2

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.7430. Min Act: -0.0000

Data Index: 578918 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.6952. Min Act: -0.0000

Data Index: 517459 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.6567. Min Act: -0.0000

Data Index: 1206384 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.6535. Min Act: -0.0000

Data Index: 1107209 (C4 (Web Text))

Max Activating Token Index: 870

Text #6

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.6042. Min Act: -0.0000

Data Index: 597721 (C4 (Web Text))

Max Activating Token Index: 735

Text #7

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.6112. Min Act: -0.0001

Data Index: 775547 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.5957. Min Act: -0.0000

Data Index: 1093719 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.6089. Min Act: -0.0001

Data Index: 570767 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.6372. Min Act: -0.0001

Data Index: 222545 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.5697. Min Act: -0.0001

Data Index: 652446 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.6074. Min Act: -0.0000

Data Index: 1273878 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.6020. Min Act: -0.0000

Data Index: 667841 (C4 (Web Text))

Max Activating Token Index: 462

Text #14

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.6016. Min Act: -0.0000

Data Index: 988358 (C4 (Web Text))

Max Activating Token Index: 998

Text #15

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.5805. Min Act: -0.0000

Data Index: 834819 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.5976. Min Act: -0.0000

Data Index: 63319 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.6503. Min Act: -0.0000

Data Index: 1313606 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.5727. Min Act: -0.0000

Data Index: 858794 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.5897. Min Act: -0.0000

Data Index: 422366 (C4 (Web Text))

Max Activating Token Index: 682