Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5904 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.1095. Min Act: -0.0001

Data Index: 719276 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0992. Min Act: -0.0001

Data Index: 156531 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.1050. Min Act: -0.0001

Data Index: 872699 (C4 (Web Text))

Max Activating Token Index: 412

Text #3

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.1003. Min Act: -0.0001

Data Index: 1209857 (C4 (Web Text))

Max Activating Token Index: 374

Text #4

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0941. Min Act: -0.0001

Data Index: 1193167 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.1019. Min Act: -0.0001

Data Index: 119550 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.1045. Min Act: -0.0001

Data Index: 1015799 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0979. Min Act: -0.0001

Data Index: 45253 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0921. Min Act: -0.0001

Data Index: 68993 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0925. Min Act: -0.0001

Data Index: 238771 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0886. Min Act: -0.0001

Data Index: 434344 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0910. Min Act: -0.0001

Data Index: 60010 (C4 (Web Text))

Max Activating Token Index: 455

Text #12

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0877. Min Act: -0.0001

Data Index: 350522 (C4 (Web Text))

Max Activating Token Index: 339

Text #13

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.1000. Min Act: -0.0001

Data Index: 594358 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0921. Min Act: -0.0001

Data Index: 913621 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0795. Min Act: -0.0001

Data Index: 343293 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0918. Min Act: -0.0001

Data Index: 630510 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0814. Min Act: -0.0001

Data Index: 337868 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0886. Min Act: -0.0001

Data Index: 525439 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0864. Min Act: -0.0001

Data Index: 970582 (C4 (Web Text))

Max Activating Token Index: 717