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

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

Neuron 1513 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.1051. Min Act: -0.0001

Data Index: 272522 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.1052. Min Act: -0.0001

Data Index: 798576 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.1012. Min Act: -0.0001

Data Index: 71661 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.1037. Min Act: -0.0001

Data Index: 777402 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.1034. Min Act: -0.0001

Data Index: 1334506 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.1020. Min Act: -0.0001

Data Index: 320110 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.1051. Min Act: -0.0001

Data Index: 464311 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0974. Min Act: -0.0001

Data Index: 18954 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.1000. Min Act: -0.0001

Data Index: 466671 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0992. Min Act: -0.0001

Data Index: 50300 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.1020. Min Act: -0.0001

Data Index: 992287 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.1016. Min Act: -0.0001

Data Index: 28629 (C4 (Web Text))

Max Activating Token Index: 459

Text #12

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0983. Min Act: -0.0001

Data Index: 40302 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.1009. Min Act: -0.0001

Data Index: 406646 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0962. Min Act: -0.0001

Data Index: 310918 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.1011. Min Act: -0.0001

Data Index: 630295 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0979. Min Act: -0.0001

Data Index: 675346 (C4 (Web Text))

Max Activating Token Index: 274

Text #17

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0869. Min Act: -0.0001

Data Index: 924039 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0891. Min Act: -0.0001

Data Index: 499674 (C4 (Web Text))

Max Activating Token Index: 568

Text #19

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0962. Min Act: -0.0001

Data Index: 524995 (C4 (Web Text))

Max Activating Token Index: 842