Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1952 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.1199. Min Act: -0.0006

Data Index: 389254 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.1123. Min Act: -0.0006

Data Index: 452826 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0955. Min Act: -0.0006

Data Index: 390381 (C4 (Web Text))

Max Activating Token Index: 574

Text #3

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0944. Min Act: -0.0006

Data Index: 182789 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0877. Min Act: -0.0006

Data Index: 483403 (C4 (Web Text))

Max Activating Token Index: 896

Text #5

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0958. Min Act: -0.0006

Data Index: 552284 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0921. Min Act: -0.0006

Data Index: 824222 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0950. Min Act: -0.0006

Data Index: 337603 (C4 (Web Text))

Max Activating Token Index: 677

Text #8

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0844. Min Act: -0.0006

Data Index: 849082 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0966. Min Act: -0.0006

Data Index: 346669 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0777. Min Act: -0.0006

Data Index: 695531 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0938. Min Act: -0.0006

Data Index: 1028728 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0870. Min Act: -0.0006

Data Index: 62193 (C4 (Web Text))

Max Activating Token Index: 721

Text #13

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0744. Min Act: -0.0005

Data Index: 90280 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0827. Min Act: -0.0006

Data Index: 1338440 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0789. Min Act: -0.0006

Data Index: 309310 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0887. Min Act: -0.0006

Data Index: 152678 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0845. Min Act: -0.0006

Data Index: 404852 (C4 (Web Text))

Max Activating Token Index: 731

Text #18

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0840. Min Act: -0.0006

Data Index: 1327897 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0722. Min Act: -0.0006

Data Index: 203300 (C4 (Web Text))

Max Activating Token Index: 525