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

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

Neuron 2397 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4755. Min Range: -0.4755

Max Act: 0.4755. Min Act: -0.0000

Data Index: 513839 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 0.4755. Min Range: -0.4755

Max Act: 0.4457. Min Act: -0.0000

Data Index: 1632233 (Python Code)

Max Activating Token Index: 740

Text #2

Max Range: 0.4755. Min Range: -0.4755

Max Act: 0.4222. Min Act: -0.0000

Data Index: 124751 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 0.4755. Min Range: -0.4755

Max Act: 0.4049. Min Act: -0.0000

Data Index: 493178 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 0.4755. Min Range: -0.4755

Max Act: 0.4105. Min Act: -0.0000

Data Index: 1001119 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 0.4755. Min Range: -0.4755

Max Act: 0.4019. Min Act: -0.0000

Data Index: 1377389 (Python Code)

Max Activating Token Index: 170

Text #6

Max Range: 0.4755. Min Range: -0.4755

Max Act: 0.4109. Min Act: -0.0000

Data Index: 1243433 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 0.4755. Min Range: -0.4755

Max Act: 0.4002. Min Act: -0.0000

Data Index: 777676 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 0.4755. Min Range: -0.4755

Max Act: 0.4135. Min Act: -0.0000

Data Index: 1192874 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 0.4755. Min Range: -0.4755

Max Act: 0.4049. Min Act: -0.0000

Data Index: 1497274 (Python Code)

Max Activating Token Index: 192

Text #10

Max Range: 0.4755. Min Range: -0.4755

Max Act: 0.3925. Min Act: -0.0000

Data Index: 426420 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 0.4755. Min Range: -0.4755

Max Act: 0.3886. Min Act: -0.0000

Data Index: 507964 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 0.4755. Min Range: -0.4755

Max Act: 0.4013. Min Act: -0.0000

Data Index: 1286639 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 0.4755. Min Range: -0.4755

Max Act: 0.3809. Min Act: -0.0000

Data Index: 766748 (C4 (Web Text))

Max Activating Token Index: 335

Text #14

Max Range: 0.4755. Min Range: -0.4755

Max Act: 0.4074. Min Act: -0.0000

Data Index: 255047 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 0.4755. Min Range: -0.4755

Max Act: 0.3773. Min Act: -0.0000

Data Index: 1456330 (Python Code)

Max Activating Token Index: 95

Text #16

Max Range: 0.4755. Min Range: -0.4755

Max Act: 0.3861. Min Act: -0.0000

Data Index: 611487 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 0.4755. Min Range: -0.4755

Max Act: 0.3767. Min Act: -0.0000

Data Index: 429349 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 0.4755. Min Range: -0.4755

Max Act: 0.3760. Min Act: -0.0000

Data Index: 465132 (C4 (Web Text))

Max Activating Token Index: 543

Text #19

Max Range: 0.4755. Min Range: -0.4755

Max Act: 0.3828. Min Act: -0.0000

Data Index: 943206 (C4 (Web Text))

Max Activating Token Index: 32