Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2374 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.8012. Min Act: -0.0001

Data Index: 715753 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.5861. Min Act: -0.0002

Data Index: 169101 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.7615. Min Act: -0.0002

Data Index: 320072 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.7155. Min Act: -0.0001

Data Index: 979013 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6979. Min Act: -0.0001

Data Index: 839743 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.5801. Min Act: -0.0001

Data Index: 689122 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6645. Min Act: -0.0001

Data Index: 1300480 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6141. Min Act: -0.0001

Data Index: 33652 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.7631. Min Act: -0.0002

Data Index: 1284090 (C4 (Web Text))

Max Activating Token Index: 559

Text #9

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6863. Min Act: -0.0001

Data Index: 125120 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6637. Min Act: -0.0002

Data Index: 245904 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.5713. Min Act: -0.0001

Data Index: 791994 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6664. Min Act: -0.0002

Data Index: 1287913 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.4462. Min Act: -0.0001

Data Index: 260282 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6601. Min Act: -0.0002

Data Index: 187770 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.5929. Min Act: -0.0001

Data Index: 157259 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6758. Min Act: -0.0002

Data Index: 717312 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.5452. Min Act: -0.0001

Data Index: 1152477 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.5959. Min Act: -0.0001

Data Index: 1258387 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.5707. Min Act: -0.0001

Data Index: 362491 (C4 (Web Text))

Max Activating Token Index: 559