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

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

Neuron 3625 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: 2.6902. Min Range: -2.6902

Max Act: 2.6902. Min Act: -0.0000

Data Index: 127775 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 2.6902. Min Range: -2.6902

Max Act: 2.6856. Min Act: -0.0000

Data Index: 150661 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 2.6902. Min Range: -2.6902

Max Act: 2.4988. Min Act: -0.0000

Data Index: 1153987 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 2.6902. Min Range: -2.6902

Max Act: 2.5061. Min Act: -0.0000

Data Index: 307048 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 2.6902. Min Range: -2.6902

Max Act: 2.2612. Min Act: -0.0000

Data Index: 374089 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 2.6902. Min Range: -2.6902

Max Act: 2.2414. Min Act: -0.0000

Data Index: 795652 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 2.6902. Min Range: -2.6902

Max Act: 2.3308. Min Act: -0.0000

Data Index: 936346 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 2.6902. Min Range: -2.6902

Max Act: 2.1227. Min Act: -0.0000

Data Index: 426900 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 2.6902. Min Range: -2.6902

Max Act: 2.2325. Min Act: -0.0000

Data Index: 939313 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 2.6902. Min Range: -2.6902

Max Act: 2.2055. Min Act: -0.0000

Data Index: 1092289 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 2.6902. Min Range: -2.6902

Max Act: 2.2118. Min Act: -0.0000

Data Index: 1301475 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 2.6902. Min Range: -2.6902

Max Act: 2.2033. Min Act: -0.0000

Data Index: 1035949 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 2.6902. Min Range: -2.6902

Max Act: 2.2128. Min Act: -0.0000

Data Index: 353189 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 2.6902. Min Range: -2.6902

Max Act: 2.2039. Min Act: -0.0000

Data Index: 1309602 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 2.6902. Min Range: -2.6902

Max Act: 2.1901. Min Act: -0.0000

Data Index: 1029461 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 2.6902. Min Range: -2.6902

Max Act: 2.1830. Min Act: -0.0000

Data Index: 529852 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 2.6902. Min Range: -2.6902

Max Act: 2.1698. Min Act: -0.0000

Data Index: 616804 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 2.6902. Min Range: -2.6902

Max Act: 2.2753. Min Act: -0.0000

Data Index: 63621 (C4 (Web Text))

Max Activating Token Index: 168

Text #18

Max Range: 2.6902. Min Range: -2.6902

Max Act: 2.0444. Min Act: -0.0000

Data Index: 601293 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 2.6902. Min Range: -2.6902

Max Act: 2.1550. Min Act: -0.0000

Data Index: 650601 (C4 (Web Text))

Max Activating Token Index: 257