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

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

Neuron 822 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: 2.1067. Min Range: -2.1067

Max Act: 2.0210. Min Act: -0.0000

Data Index: 272610 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.8932. Min Act: -0.0000

Data Index: 880055 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.8300. Min Act: -0.0000

Data Index: 871747 (C4 (Web Text))

Max Activating Token Index: 771

Text #3

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.9888. Min Act: -0.0000

Data Index: 961346 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 2.1067. Min Range: -2.1067

Max Act: 2.1067. Min Act: -0.0000

Data Index: 736581 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.8529. Min Act: -0.0000

Data Index: 1119231 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.7980. Min Act: -0.0000

Data Index: 147990 (C4 (Web Text))

Max Activating Token Index: 877

Text #7

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.7928. Min Act: -0.0000

Data Index: 1156671 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.7931. Min Act: -0.0000

Data Index: 418712 (C4 (Web Text))

Max Activating Token Index: 977

Text #9

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.6445. Min Act: -0.0000

Data Index: 722083 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.6466. Min Act: -0.0000

Data Index: 417664 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.5983. Min Act: -0.0000

Data Index: 1114721 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.6121. Min Act: -0.0000

Data Index: 1230874 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.6698. Min Act: -0.0000

Data Index: 453901 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.7440. Min Act: -0.0000

Data Index: 851337 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.5990. Min Act: -0.0000

Data Index: 190951 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.6686. Min Act: -0.0000

Data Index: 793579 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.6360. Min Act: -0.0000

Data Index: 1237167 (C4 (Web Text))

Max Activating Token Index: 538

Text #18

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.6364. Min Act: -0.0000

Data Index: 453403 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.7149. Min Act: -0.0000

Data Index: 1045015 (C4 (Web Text))

Max Activating Token Index: 528