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

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

Neuron 3928 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0005. Min Range: -2.0005

Max Act: 2.0005. Min Act: -0.0000

Data Index: 593836 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 2.0005. Min Range: -2.0005

Max Act: 1.5390. Min Act: -0.0000

Data Index: 1118060 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 2.0005. Min Range: -2.0005

Max Act: 1.5039. Min Act: -0.0000

Data Index: 113233 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 2.0005. Min Range: -2.0005

Max Act: 1.3630. Min Act: -0.0000

Data Index: 327282 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 2.0005. Min Range: -2.0005

Max Act: 1.0229. Min Act: 0.0000

Data Index: 1041449 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 2.0005. Min Range: -2.0005

Max Act: 1.0544. Min Act: -0.0000

Data Index: 585600 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 2.0005. Min Range: -2.0005

Max Act: 1.0074. Min Act: -0.0000

Data Index: 335922 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 2.0005. Min Range: -2.0005

Max Act: 0.9835. Min Act: -0.0000

Data Index: 597688 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 2.0005. Min Range: -2.0005

Max Act: 0.9555. Min Act: -0.0000

Data Index: 108324 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 2.0005. Min Range: -2.0005

Max Act: 0.9510. Min Act: -0.0000

Data Index: 641757 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 2.0005. Min Range: -2.0005

Max Act: 0.9870. Min Act: -0.0000

Data Index: 1324406 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 2.0005. Min Range: -2.0005

Max Act: 0.9223. Min Act: -0.0000

Data Index: 199575 (C4 (Web Text))

Max Activating Token Index: 73

Text #12

Max Range: 2.0005. Min Range: -2.0005

Max Act: 0.8891. Min Act: -0.0000

Data Index: 965689 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 2.0005. Min Range: -2.0005

Max Act: 0.9396. Min Act: -0.0000

Data Index: 1152124 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 2.0005. Min Range: -2.0005

Max Act: 0.8686. Min Act: -0.0000

Data Index: 858366 (C4 (Web Text))

Max Activating Token Index: 991

Text #15

Max Range: 2.0005. Min Range: -2.0005

Max Act: 0.8650. Min Act: -0.0000

Data Index: 100114 (C4 (Web Text))

Max Activating Token Index: 363

Text #16

Max Range: 2.0005. Min Range: -2.0005

Max Act: 0.8355. Min Act: -0.0000

Data Index: 764747 (C4 (Web Text))

Max Activating Token Index: 554

Text #17

Max Range: 2.0005. Min Range: -2.0005

Max Act: 0.8085. Min Act: -0.0000

Data Index: 927492 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 2.0005. Min Range: -2.0005

Max Act: 0.7254. Min Act: -0.0000

Data Index: 213155 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 2.0005. Min Range: -2.0005

Max Act: 0.7367. Min Act: -0.0000

Data Index: 489585 (C4 (Web Text))

Max Activating Token Index: 563