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

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

Neuron 657 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0990. Min Range: -1.0990

Max Act: 1.0286. Min Act: -0.0002

Data Index: 698435 (C4 (Web Text))

Max Activating Token Index: 187

Text #1

Max Range: 1.0990. Min Range: -1.0990

Max Act: 1.0990. Min Act: -0.0002

Data Index: 590731 (C4 (Web Text))

Max Activating Token Index: 564

Text #2

Max Range: 1.0990. Min Range: -1.0990

Max Act: 0.9997. Min Act: -0.0002

Data Index: 1298548 (C4 (Web Text))

Max Activating Token Index: 535

Text #3

Max Range: 1.0990. Min Range: -1.0990

Max Act: 0.9585. Min Act: -0.0002

Data Index: 949177 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 1.0990. Min Range: -1.0990

Max Act: 0.9056. Min Act: -0.0002

Data Index: 1157383 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 1.0990. Min Range: -1.0990

Max Act: 0.7045. Min Act: -0.0002

Data Index: 982638 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 1.0990. Min Range: -1.0990

Max Act: 0.9721. Min Act: -0.0002

Data Index: 997358 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 1.0990. Min Range: -1.0990

Max Act: 0.7748. Min Act: -0.0002

Data Index: 130453 (C4 (Web Text))

Max Activating Token Index: 230

Text #8

Max Range: 1.0990. Min Range: -1.0990

Max Act: 0.7627. Min Act: -0.0002

Data Index: 851854 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 1.0990. Min Range: -1.0990

Max Act: 0.7999. Min Act: -0.0002

Data Index: 645229 (C4 (Web Text))

Max Activating Token Index: 281

Text #10

Max Range: 1.0990. Min Range: -1.0990

Max Act: 0.8208. Min Act: -0.0002

Data Index: 767177 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 1.0990. Min Range: -1.0990

Max Act: 0.8599. Min Act: -0.0002

Data Index: 23501 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 1.0990. Min Range: -1.0990

Max Act: 0.7815. Min Act: -0.0002

Data Index: 216704 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 1.0990. Min Range: -1.0990

Max Act: 0.8715. Min Act: -0.0002

Data Index: 916716 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 1.0990. Min Range: -1.0990

Max Act: 0.7959. Min Act: -0.0002

Data Index: 705658 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 1.0990. Min Range: -1.0990

Max Act: 0.9308. Min Act: -0.0002

Data Index: 1174889 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 1.0990. Min Range: -1.0990

Max Act: 0.8761. Min Act: -0.0002

Data Index: 899680 (C4 (Web Text))

Max Activating Token Index: 212

Text #17

Max Range: 1.0990. Min Range: -1.0990

Max Act: 0.8917. Min Act: -0.0002

Data Index: 28028 (C4 (Web Text))

Max Activating Token Index: 260

Text #18

Max Range: 1.0990. Min Range: -1.0990

Max Act: 0.8280. Min Act: -0.0002

Data Index: 739148 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 1.0990. Min Range: -1.0990

Max Act: 0.8999. Min Act: -0.0002

Data Index: 411190 (C4 (Web Text))

Max Activating Token Index: 166