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

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

Neuron 87 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1221. Min Act: -0.0000

Data Index: 424601 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1056. Min Act: -0.0001

Data Index: 1082010 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0994. Min Act: -0.0001

Data Index: 918581 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0991. Min Act: -0.0001

Data Index: 510427 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1023. Min Act: -0.0001

Data Index: 949787 (C4 (Web Text))

Max Activating Token Index: 759

Text #5

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0955. Min Act: -0.0001

Data Index: 1049525 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0934. Min Act: 0.0000

Data Index: 1078769 (C4 (Web Text))

Max Activating Token Index: 293

Text #7

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0929. Min Act: -0.0001

Data Index: 1271807 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0959. Min Act: -0.0000

Data Index: 541919 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0955. Min Act: -0.0001

Data Index: 1191577 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0946. Min Act: -0.0001

Data Index: 149373 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0980. Min Act: -0.0001

Data Index: 899574 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0904. Min Act: -0.0001

Data Index: 648541 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0872. Min Act: -0.0001

Data Index: 1347575 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0918. Min Act: -0.0001

Data Index: 1158512 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0906. Min Act: -0.0001

Data Index: 27707 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0907. Min Act: -0.0001

Data Index: 412483 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0902. Min Act: -0.0001

Data Index: 1060762 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0865. Min Act: -0.0001

Data Index: 1260428 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0893. Min Act: -0.0001

Data Index: 687599 (C4 (Web Text))

Max Activating Token Index: 37