Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1413 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1420. Min Range: -1.1420

Max Act: 1.1191. Min Act: -0.0001

Data Index: 229968 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 1.1420. Min Range: -1.1420

Max Act: 1.0624. Min Act: -0.0002

Data Index: 271819 (C4 (Web Text))

Max Activating Token Index: 618

Text #2

Max Range: 1.1420. Min Range: -1.1420

Max Act: 1.0315. Min Act: -0.0001

Data Index: 172463 (C4 (Web Text))

Max Activating Token Index: 354

Text #3

Max Range: 1.1420. Min Range: -1.1420

Max Act: 1.0970. Min Act: -0.0002

Data Index: 1039713 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.9851. Min Act: -0.0001

Data Index: 328976 (C4 (Web Text))

Max Activating Token Index: 401

Text #5

Max Range: 1.1420. Min Range: -1.1420

Max Act: 1.0471. Min Act: -0.0001

Data Index: 1311007 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.9888. Min Act: -0.0002

Data Index: 145524 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 1.1420. Min Range: -1.1420

Max Act: 1.0041. Min Act: -0.0001

Data Index: 744867 (C4 (Web Text))

Max Activating Token Index: 460

Text #8

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.9339. Min Act: -0.0002

Data Index: 1001041 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.8482. Min Act: -0.0001

Data Index: 287939 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.8998. Min Act: -0.0002

Data Index: 47285 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.9333. Min Act: -0.0002

Data Index: 711083 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.9521. Min Act: -0.0001

Data Index: 524612 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.9631. Min Act: -0.0002

Data Index: 841185 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.9694. Min Act: -0.0001

Data Index: 207441 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 1.1420. Min Range: -1.1420

Max Act: 1.1420. Min Act: -0.0001

Data Index: 863149 (C4 (Web Text))

Max Activating Token Index: 941

Text #16

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.9340. Min Act: -0.0001

Data Index: 599080 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.8704. Min Act: -0.0001

Data Index: 666619 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.8617. Min Act: -0.0002

Data Index: 758115 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.9479. Min Act: -0.0002

Data Index: 728826 (C4 (Web Text))

Max Activating Token Index: 308