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

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

Neuron 1660 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: 0.1074. Min Range: -0.1074

Max Act: 0.1058. Min Act: -0.0003

Data Index: 392087 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0898. Min Act: -0.0003

Data Index: 674687 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0941. Min Act: -0.0003

Data Index: 562444 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0945. Min Act: -0.0003

Data Index: 188167 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0950. Min Act: -0.0003

Data Index: 942290 (C4 (Web Text))

Max Activating Token Index: 209

Text #5

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0933. Min Act: -0.0003

Data Index: 758259 (C4 (Web Text))

Max Activating Token Index: 931

Text #6

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.1074. Min Act: -0.0003

Data Index: 1040554 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0935. Min Act: -0.0003

Data Index: 637935 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0876. Min Act: -0.0003

Data Index: 644851 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0944. Min Act: -0.0003

Data Index: 689100 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0896. Min Act: -0.0003

Data Index: 687448 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0854. Min Act: -0.0003

Data Index: 401881 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0881. Min Act: -0.0003

Data Index: 1207934 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0861. Min Act: -0.0003

Data Index: 1254269 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0895. Min Act: -0.0003

Data Index: 469730 (C4 (Web Text))

Max Activating Token Index: 108

Text #15

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0747. Min Act: -0.0003

Data Index: 537786 (C4 (Web Text))

Max Activating Token Index: 633

Text #16

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0864. Min Act: -0.0003

Data Index: 1048731 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0863. Min Act: -0.0003

Data Index: 1323099 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0765. Min Act: -0.0003

Data Index: 278620 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0800. Min Act: -0.0003

Data Index: 1299569 (C4 (Web Text))

Max Activating Token Index: 708