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

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

Neuron 2375 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0708. Min Range: -2.0708

Max Act: 2.0708. Min Act: -0.0000

Data Index: 965866 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 2.0708. Min Range: -2.0708

Max Act: 2.0229. Min Act: -0.0000

Data Index: 1325706 (C4 (Web Text))

Max Activating Token Index: 870

Text #2

Max Range: 2.0708. Min Range: -2.0708

Max Act: 1.8976. Min Act: -0.0000

Data Index: 1066696 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 2.0708. Min Range: -2.0708

Max Act: 1.9456. Min Act: -0.0000

Data Index: 1067806 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 2.0708. Min Range: -2.0708

Max Act: 1.9163. Min Act: -0.0000

Data Index: 308291 (C4 (Web Text))

Max Activating Token Index: 977

Text #5

Max Range: 2.0708. Min Range: -2.0708

Max Act: 1.8957. Min Act: -0.0000

Data Index: 627329 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 2.0708. Min Range: -2.0708

Max Act: 1.8753. Min Act: -0.0000

Data Index: 1326682 (C4 (Web Text))

Max Activating Token Index: 690

Text #7

Max Range: 2.0708. Min Range: -2.0708

Max Act: 1.8433. Min Act: -0.0000

Data Index: 1232347 (C4 (Web Text))

Max Activating Token Index: 818

Text #8

Max Range: 2.0708. Min Range: -2.0708

Max Act: 1.8365. Min Act: -0.0000

Data Index: 605020 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 2.0708. Min Range: -2.0708

Max Act: 1.8126. Min Act: -0.0000

Data Index: 166031 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 2.0708. Min Range: -2.0708

Max Act: 1.7957. Min Act: -0.0000

Data Index: 1144607 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 2.0708. Min Range: -2.0708

Max Act: 1.7927. Min Act: -0.0000

Data Index: 146499 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 2.0708. Min Range: -2.0708

Max Act: 1.7588. Min Act: -0.0000

Data Index: 510639 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 2.0708. Min Range: -2.0708

Max Act: 1.6521. Min Act: -0.0000

Data Index: 615529 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 2.0708. Min Range: -2.0708

Max Act: 1.7447. Min Act: -0.0000

Data Index: 214432 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 2.0708. Min Range: -2.0708

Max Act: 1.7361. Min Act: -0.0000

Data Index: 155782 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 2.0708. Min Range: -2.0708

Max Act: 1.6374. Min Act: -0.0000

Data Index: 1196909 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 2.0708. Min Range: -2.0708

Max Act: 1.6376. Min Act: -0.0000

Data Index: 323642 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 2.0708. Min Range: -2.0708

Max Act: 1.7262. Min Act: -0.0000

Data Index: 1143238 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 2.0708. Min Range: -2.0708

Max Act: 1.7081. Min Act: -0.0000

Data Index: 1296190 (C4 (Web Text))

Max Activating Token Index: 680