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

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

Neuron 1050 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.8017. Min Act: -0.0000

Data Index: 472373 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.6538. Min Act: -0.0000

Data Index: 771095 (C4 (Web Text))

Max Activating Token Index: 749

Text #2

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.6291. Min Act: -0.0000

Data Index: 812961 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.6438. Min Act: -0.0000

Data Index: 29807 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.6024. Min Act: -0.0000

Data Index: 53812 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.5855. Min Act: -0.0000

Data Index: 270300 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.6091. Min Act: -0.0000

Data Index: 393564 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.5313. Min Act: -0.0000

Data Index: 668706 (C4 (Web Text))

Max Activating Token Index: 607

Text #8

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.4697. Min Act: -0.0000

Data Index: 28875 (C4 (Web Text))

Max Activating Token Index: 937

Text #9

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.5027. Min Act: -0.0000

Data Index: 1013419 (C4 (Web Text))

Max Activating Token Index: 865

Text #10

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.5612. Min Act: -0.0000

Data Index: 863169 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.5005. Min Act: -0.0000

Data Index: 244543 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.5380. Min Act: -0.0000

Data Index: 448968 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.3800. Min Act: -0.0000

Data Index: 432312 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.3169. Min Act: -0.0000

Data Index: 1118784 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.4155. Min Act: -0.0000

Data Index: 909548 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.5115. Min Act: -0.0000

Data Index: 138649 (C4 (Web Text))

Max Activating Token Index: 741

Text #17

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.4489. Min Act: -0.0000

Data Index: 1273377 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.4340. Min Act: -0.0000

Data Index: 760255 (C4 (Web Text))

Max Activating Token Index: 106

Text #19

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.4124. Min Act: -0.0000

Data Index: 688030 (C4 (Web Text))

Max Activating Token Index: 24