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

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

Neuron 3744 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3555. Min Range: -2.3555

Max Act: 2.3555. Min Act: -0.0000

Data Index: 218948 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 2.3555. Min Range: -2.3555

Max Act: 2.1023. Min Act: -0.0000

Data Index: 877401 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 2.3555. Min Range: -2.3555

Max Act: 1.8933. Min Act: -0.0000

Data Index: 1234869 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 2.3555. Min Range: -2.3555

Max Act: 1.9345. Min Act: -0.0000

Data Index: 1239789 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 2.3555. Min Range: -2.3555

Max Act: 1.9014. Min Act: -0.0000

Data Index: 83013 (C4 (Web Text))

Max Activating Token Index: 933

Text #5

Max Range: 2.3555. Min Range: -2.3555

Max Act: 1.7767. Min Act: -0.0000

Data Index: 928029 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 2.3555. Min Range: -2.3555

Max Act: 1.8440. Min Act: -0.0000

Data Index: 151776 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 2.3555. Min Range: -2.3555

Max Act: 1.7455. Min Act: -0.0000

Data Index: 487580 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 2.3555. Min Range: -2.3555

Max Act: 1.7392. Min Act: -0.0000

Data Index: 1131302 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 2.3555. Min Range: -2.3555

Max Act: 1.7119. Min Act: -0.0000

Data Index: 827332 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 2.3555. Min Range: -2.3555

Max Act: 1.7250. Min Act: -0.0000

Data Index: 647482 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 2.3555. Min Range: -2.3555

Max Act: 1.8144. Min Act: -0.0000

Data Index: 1038934 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 2.3555. Min Range: -2.3555

Max Act: 1.6814. Min Act: -0.0000

Data Index: 63881 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 2.3555. Min Range: -2.3555

Max Act: 1.7400. Min Act: -0.0000

Data Index: 1129261 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 2.3555. Min Range: -2.3555

Max Act: 1.7308. Min Act: -0.0000

Data Index: 307132 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 2.3555. Min Range: -2.3555

Max Act: 1.4556. Min Act: -0.0000

Data Index: 681745 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 2.3555. Min Range: -2.3555

Max Act: 1.5581. Min Act: -0.0000

Data Index: 576474 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 2.3555. Min Range: -2.3555

Max Act: 1.6071. Min Act: -0.0000

Data Index: 74337 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 2.3555. Min Range: -2.3555

Max Act: 1.6771. Min Act: -0.0000

Data Index: 438346 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 2.3555. Min Range: -2.3555

Max Act: 1.5978. Min Act: -0.0000

Data Index: 533561 (C4 (Web Text))

Max Activating Token Index: 362