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

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

Neuron 1893 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3801. Min Range: -2.3801

Max Act: 2.3801. Min Act: -0.0000

Data Index: 990829 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 2.3801. Min Range: -2.3801

Max Act: 1.7894. Min Act: -0.0000

Data Index: 649786 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 2.3801. Min Range: -2.3801

Max Act: 1.7610. Min Act: -0.0000

Data Index: 1155233 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 2.3801. Min Range: -2.3801

Max Act: 1.8308. Min Act: -0.0000

Data Index: 885546 (C4 (Web Text))

Max Activating Token Index: 647

Text #4

Max Range: 2.3801. Min Range: -2.3801

Max Act: 1.6756. Min Act: -0.0000

Data Index: 1273237 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 2.3801. Min Range: -2.3801

Max Act: 1.6731. Min Act: -0.0000

Data Index: 936679 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 2.3801. Min Range: -2.3801

Max Act: 1.5355. Min Act: -0.0000

Data Index: 249586 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 2.3801. Min Range: -2.3801

Max Act: 1.5861. Min Act: -0.0000

Data Index: 427380 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 2.3801. Min Range: -2.3801

Max Act: 1.6532. Min Act: -0.0000

Data Index: 242883 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 2.3801. Min Range: -2.3801

Max Act: 1.4731. Min Act: -0.0000

Data Index: 115918 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 2.3801. Min Range: -2.3801

Max Act: 1.4548. Min Act: -0.0000

Data Index: 706038 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 2.3801. Min Range: -2.3801

Max Act: 1.6150. Min Act: -0.0000

Data Index: 494935 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 2.3801. Min Range: -2.3801

Max Act: 1.4946. Min Act: -0.0000

Data Index: 1014083 (C4 (Web Text))

Max Activating Token Index: 884

Text #13

Max Range: 2.3801. Min Range: -2.3801

Max Act: 1.3512. Min Act: -0.0000

Data Index: 1190744 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 2.3801. Min Range: -2.3801

Max Act: 1.5674. Min Act: -0.0000

Data Index: 948719 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 2.3801. Min Range: -2.3801

Max Act: 1.3803. Min Act: -0.0000

Data Index: 86349 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 2.3801. Min Range: -2.3801

Max Act: 1.3574. Min Act: -0.0000

Data Index: 223654 (C4 (Web Text))

Max Activating Token Index: 212

Text #17

Max Range: 2.3801. Min Range: -2.3801

Max Act: 1.5374. Min Act: -0.0000

Data Index: 1116035 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 2.3801. Min Range: -2.3801

Max Act: 1.4599. Min Act: -0.0000

Data Index: 464675 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 2.3801. Min Range: -2.3801

Max Act: 1.4314. Min Act: -0.0000

Data Index: 401181 (C4 (Web Text))

Max Activating Token Index: 755