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

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

Neuron 269 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: 0.1102. Min Range: -0.1102

Max Act: 0.1102. Min Act: -0.0001

Data Index: 166891 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0970. Min Act: -0.0001

Data Index: 183952 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.1090. Min Act: -0.0001

Data Index: 447134 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.1002. Min Act: -0.0001

Data Index: 312957 (C4 (Web Text))

Max Activating Token Index: 590

Text #4

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.1044. Min Act: -0.0001

Data Index: 978504 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0985. Min Act: -0.0001

Data Index: 32396 (C4 (Web Text))

Max Activating Token Index: 101

Text #6

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0923. Min Act: -0.0001

Data Index: 410602 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0863. Min Act: -0.0001

Data Index: 534003 (C4 (Web Text))

Max Activating Token Index: 736

Text #8

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0873. Min Act: -0.0001

Data Index: 1365721 (Python Code)

Max Activating Token Index: 835

Text #9

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0865. Min Act: -0.0001

Data Index: 504383 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0871. Min Act: -0.0001

Data Index: 1039189 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0860. Min Act: -0.0001

Data Index: 851779 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.1067. Min Act: -0.0001

Data Index: 111775 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0827. Min Act: -0.0001

Data Index: 174373 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0973. Min Act: -0.0001

Data Index: 223878 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0958. Min Act: -0.0001

Data Index: 552987 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0884. Min Act: -0.0001

Data Index: 1061616 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0832. Min Act: -0.0001

Data Index: 1315207 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0866. Min Act: -0.0001

Data Index: 539828 (C4 (Web Text))

Max Activating Token Index: 238

Text #19

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0953. Min Act: -0.0001

Data Index: 713777 (C4 (Web Text))

Max Activating Token Index: 648