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

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

Neuron 1370 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1130. Min Range: -1.1130

Max Act: 1.0149. Min Act: -0.0000

Data Index: 1312248 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 1.1130. Min Range: -1.1130

Max Act: 1.1130. Min Act: -0.0000

Data Index: 1093576 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 1.1130. Min Range: -1.1130

Max Act: 1.0368. Min Act: -0.0000

Data Index: 203140 (C4 (Web Text))

Max Activating Token Index: 559

Text #3

Max Range: 1.1130. Min Range: -1.1130

Max Act: 1.0174. Min Act: -0.0000

Data Index: 494500 (C4 (Web Text))

Max Activating Token Index: 649

Text #4

Max Range: 1.1130. Min Range: -1.1130

Max Act: 0.9839. Min Act: -0.0000

Data Index: 710304 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 1.1130. Min Range: -1.1130

Max Act: 0.9406. Min Act: -0.0000

Data Index: 832220 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 1.1130. Min Range: -1.1130

Max Act: 0.8697. Min Act: -0.0000

Data Index: 198930 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 1.1130. Min Range: -1.1130

Max Act: 0.9507. Min Act: -0.0000

Data Index: 1340426 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 1.1130. Min Range: -1.1130

Max Act: 0.9152. Min Act: -0.0000

Data Index: 173208 (C4 (Web Text))

Max Activating Token Index: 753

Text #9

Max Range: 1.1130. Min Range: -1.1130

Max Act: 0.9057. Min Act: -0.0000

Data Index: 232309 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 1.1130. Min Range: -1.1130

Max Act: 0.8913. Min Act: -0.0000

Data Index: 1001159 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 1.1130. Min Range: -1.1130

Max Act: 0.8962. Min Act: -0.0000

Data Index: 766672 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 1.1130. Min Range: -1.1130

Max Act: 0.8332. Min Act: -0.0000

Data Index: 1032599 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 1.1130. Min Range: -1.1130

Max Act: 0.8907. Min Act: -0.0000

Data Index: 806379 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 1.1130. Min Range: -1.1130

Max Act: 0.8609. Min Act: -0.0000

Data Index: 941125 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 1.1130. Min Range: -1.1130

Max Act: 0.8799. Min Act: -0.0000

Data Index: 1058460 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 1.1130. Min Range: -1.1130

Max Act: 0.7761. Min Act: -0.0000

Data Index: 1278110 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 1.1130. Min Range: -1.1130

Max Act: 0.9209. Min Act: -0.0000

Data Index: 160495 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 1.1130. Min Range: -1.1130

Max Act: 0.8460. Min Act: -0.0000

Data Index: 31152 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 1.1130. Min Range: -1.1130

Max Act: 0.9616. Min Act: -0.0000

Data Index: 49984 (C4 (Web Text))

Max Activating Token Index: 825