Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2630 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1513. Min Act: -0.0003

Data Index: 215331 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1397. Min Act: -0.0003

Data Index: 1300401 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1157. Min Act: -0.0003

Data Index: 8450 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1245. Min Act: -0.0003

Data Index: 748300 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1099. Min Act: -0.0003

Data Index: 894161 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1091. Min Act: -0.0003

Data Index: 43144 (C4 (Web Text))

Max Activating Token Index: 725

Text #6

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1046. Min Act: -0.0003

Data Index: 1061295 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1103. Min Act: -0.0003

Data Index: 503913 (C4 (Web Text))

Max Activating Token Index: 461

Text #8

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1092. Min Act: -0.0003

Data Index: 1160528 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.0995. Min Act: -0.0003

Data Index: 15791 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.0915. Min Act: -0.0003

Data Index: 98166 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.0982. Min Act: -0.0003

Data Index: 1142958 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1015. Min Act: -0.0003

Data Index: 37605 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.0995. Min Act: -0.0003

Data Index: 947387 (C4 (Web Text))

Max Activating Token Index: 445

Text #14

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1035. Min Act: -0.0003

Data Index: 599635 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.0955. Min Act: -0.0003

Data Index: 596854 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.0991. Min Act: -0.0003

Data Index: 292607 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.0948. Min Act: -0.0003

Data Index: 823420 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.0945. Min Act: -0.0003

Data Index: 225660 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.0953. Min Act: -0.0003

Data Index: 963643 (C4 (Web Text))

Max Activating Token Index: 561