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

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

Neuron 5189 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.1115. Min Act: -0.0002

Data Index: 534409 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0990. Min Act: -0.0002

Data Index: 564180 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0914. Min Act: -0.0002

Data Index: 174406 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0913. Min Act: -0.0002

Data Index: 1063750 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0761. Min Act: -0.0002

Data Index: 355947 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0875. Min Act: -0.0002

Data Index: 1367848 (Python Code)

Max Activating Token Index: 337

Text #6

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0795. Min Act: -0.0002

Data Index: 1370178 (Python Code)

Max Activating Token Index: 204

Text #7

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0775. Min Act: -0.0002

Data Index: 1516108 (Python Code)

Max Activating Token Index: 109

Text #8

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0782. Min Act: -0.0002

Data Index: 1513709 (Python Code)

Max Activating Token Index: 126

Text #9

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0874. Min Act: -0.0002

Data Index: 632057 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0787. Min Act: -0.0002

Data Index: 1414888 (Python Code)

Max Activating Token Index: 451

Text #11

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0712. Min Act: -0.0002

Data Index: 175045 (C4 (Web Text))

Max Activating Token Index: 803

Text #12

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0763. Min Act: -0.0002

Data Index: 1374683 (Python Code)

Max Activating Token Index: 485

Text #13

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0729. Min Act: -0.0002

Data Index: 1391797 (Python Code)

Max Activating Token Index: 408

Text #14

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0723. Min Act: -0.0002

Data Index: 276651 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0746. Min Act: -0.0002

Data Index: 1101379 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0748. Min Act: -0.0002

Data Index: 1071223 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0718. Min Act: -0.0002

Data Index: 138358 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0714. Min Act: -0.0002

Data Index: 1634833 (Python Code)

Max Activating Token Index: 621

Text #19

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0731. Min Act: -0.0002

Data Index: 1556128 (Python Code)

Max Activating Token Index: 494