Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3699 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1945. Min Act: -0.0001

Data Index: 578167 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.0817. Min Act: -0.0001

Data Index: 1138835 (C4 (Web Text))

Max Activating Token Index: 481

Text #2

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1064. Min Act: -0.0001

Data Index: 419952 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1004. Min Act: -0.0001

Data Index: 127818 (C4 (Web Text))

Max Activating Token Index: 268

Text #4

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.0930. Min Act: -0.0001

Data Index: 826689 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.0888. Min Act: -0.0001

Data Index: 1176289 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.0821. Min Act: -0.0001

Data Index: 48634 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.0822. Min Act: -0.0000

Data Index: 257025 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.0765. Min Act: -0.0001

Data Index: 186550 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.0904. Min Act: -0.0001

Data Index: 877469 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.0805. Min Act: -0.0001

Data Index: 759065 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.0755. Min Act: -0.0001

Data Index: 553245 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.0875. Min Act: -0.0001

Data Index: 467467 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.0742. Min Act: -0.0001

Data Index: 70847 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.0731. Min Act: -0.0001

Data Index: 677303 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.0724. Min Act: -0.0001

Data Index: 1285155 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.0719. Min Act: -0.0001

Data Index: 131163 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.0718. Min Act: -0.0001

Data Index: 1148036 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.0727. Min Act: -0.0001

Data Index: 58971 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.0661. Min Act: -0.0001

Data Index: 808406 (C4 (Web Text))

Max Activating Token Index: 430