Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3571 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4645. Min Range: -1.4645

Max Act: 1.4645. Min Act: -0.0001

Data Index: 1041728 (C4 (Web Text))

Max Activating Token Index: 422

Text #1

Max Range: 1.4645. Min Range: -1.4645

Max Act: 1.3617. Min Act: -0.0001

Data Index: 721146 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 1.4645. Min Range: -1.4645

Max Act: 1.2570. Min Act: -0.0001

Data Index: 984789 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 1.4645. Min Range: -1.4645

Max Act: 1.1954. Min Act: -0.0001

Data Index: 186894 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 1.4645. Min Range: -1.4645

Max Act: 1.1699. Min Act: -0.0001

Data Index: 425985 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 1.4645. Min Range: -1.4645

Max Act: 1.1697. Min Act: -0.0001

Data Index: 12790 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 1.4645. Min Range: -1.4645

Max Act: 1.1457. Min Act: -0.0001

Data Index: 253441 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 1.4645. Min Range: -1.4645

Max Act: 1.1400. Min Act: -0.0001

Data Index: 1149233 (C4 (Web Text))

Max Activating Token Index: 943

Text #8

Max Range: 1.4645. Min Range: -1.4645

Max Act: 1.2056. Min Act: -0.0001

Data Index: 1121639 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 1.4645. Min Range: -1.4645

Max Act: 1.1676. Min Act: -0.0001

Data Index: 738449 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 1.4645. Min Range: -1.4645

Max Act: 1.0732. Min Act: -0.0001

Data Index: 579000 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 1.4645. Min Range: -1.4645

Max Act: 1.1318. Min Act: -0.0001

Data Index: 191683 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 1.4645. Min Range: -1.4645

Max Act: 1.0402. Min Act: -0.0001

Data Index: 823020 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 1.4645. Min Range: -1.4645

Max Act: 1.1093. Min Act: -0.0001

Data Index: 672650 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 1.4645. Min Range: -1.4645

Max Act: 1.1383. Min Act: -0.0001

Data Index: 158775 (C4 (Web Text))

Max Activating Token Index: 1012

Text #15

Max Range: 1.4645. Min Range: -1.4645

Max Act: 1.1603. Min Act: -0.0001

Data Index: 649794 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 1.4645. Min Range: -1.4645

Max Act: 1.0623. Min Act: -0.0001

Data Index: 414038 (C4 (Web Text))

Max Activating Token Index: 971

Text #17

Max Range: 1.4645. Min Range: -1.4645

Max Act: 1.1188. Min Act: -0.0001

Data Index: 589985 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 1.4645. Min Range: -1.4645

Max Act: 1.1419. Min Act: -0.0001

Data Index: 1356555 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 1.4645. Min Range: -1.4645

Max Act: 1.1428. Min Act: -0.0001

Data Index: 1243861 (C4 (Web Text))

Max Activating Token Index: 921