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

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

Neuron 382 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5052. Min Range: -2.5052

Max Act: 2.2858. Min Act: -0.0000

Data Index: 179488 (C4 (Web Text))

Max Activating Token Index: 861

Text #1

Max Range: 2.5052. Min Range: -2.5052

Max Act: 2.5052. Min Act: -0.0000

Data Index: 205110 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 2.5052. Min Range: -2.5052

Max Act: 2.3580. Min Act: -0.0000

Data Index: 438519 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 2.5052. Min Range: -2.5052

Max Act: 2.4323. Min Act: -0.0000

Data Index: 1076924 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 2.5052. Min Range: -2.5052

Max Act: 2.4057. Min Act: -0.0000

Data Index: 1324552 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 2.5052. Min Range: -2.5052

Max Act: 2.2714. Min Act: -0.0000

Data Index: 294912 (C4 (Web Text))

Max Activating Token Index: 653

Text #6

Max Range: 2.5052. Min Range: -2.5052

Max Act: 2.3639. Min Act: -0.0000

Data Index: 801155 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 2.5052. Min Range: -2.5052

Max Act: 2.3678. Min Act: -0.0000

Data Index: 1172445 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 2.5052. Min Range: -2.5052

Max Act: 2.3167. Min Act: -0.0000

Data Index: 1180673 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 2.5052. Min Range: -2.5052

Max Act: 2.4384. Min Act: -0.0000

Data Index: 386465 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 2.5052. Min Range: -2.5052

Max Act: 2.2614. Min Act: -0.0000

Data Index: 68231 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 2.5052. Min Range: -2.5052

Max Act: 2.1139. Min Act: -0.0000

Data Index: 664035 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 2.5052. Min Range: -2.5052

Max Act: 2.2375. Min Act: -0.0000

Data Index: 1060583 (C4 (Web Text))

Max Activating Token Index: 958

Text #13

Max Range: 2.5052. Min Range: -2.5052

Max Act: 2.1014. Min Act: -0.0000

Data Index: 936669 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 2.5052. Min Range: -2.5052

Max Act: 2.0771. Min Act: -0.0000

Data Index: 493204 (C4 (Web Text))

Max Activating Token Index: 374

Text #15

Max Range: 2.5052. Min Range: -2.5052

Max Act: 2.1877. Min Act: -0.0000

Data Index: 853630 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 2.5052. Min Range: -2.5052

Max Act: 2.0650. Min Act: -0.0000

Data Index: 242784 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 2.5052. Min Range: -2.5052

Max Act: 2.2905. Min Act: -0.0000

Data Index: 1356114 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 2.5052. Min Range: -2.5052

Max Act: 2.1618. Min Act: -0.0000

Data Index: 1315770 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 2.5052. Min Range: -2.5052

Max Act: 2.1529. Min Act: -0.0000

Data Index: 5013 (C4 (Web Text))

Max Activating Token Index: 725