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

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

Neuron 579 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6027. Min Range: -1.6027

Max Act: 1.6027. Min Act: -0.0001

Data Index: 507382 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 1.6027. Min Range: -1.6027

Max Act: 1.5660. Min Act: -0.0001

Data Index: 833417 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 1.6027. Min Range: -1.6027

Max Act: 1.4652. Min Act: -0.0001

Data Index: 850517 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 1.6027. Min Range: -1.6027

Max Act: 1.3896. Min Act: -0.0001

Data Index: 836070 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 1.6027. Min Range: -1.6027

Max Act: 1.2741. Min Act: -0.0001

Data Index: 1049082 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 1.6027. Min Range: -1.6027

Max Act: 1.1257. Min Act: -0.0001

Data Index: 155359 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 1.6027. Min Range: -1.6027

Max Act: 1.1389. Min Act: -0.0001

Data Index: 1061710 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 1.6027. Min Range: -1.6027

Max Act: 1.1284. Min Act: -0.0001

Data Index: 594516 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 1.6027. Min Range: -1.6027

Max Act: 1.1455. Min Act: -0.0001

Data Index: 1278310 (C4 (Web Text))

Max Activating Token Index: 210

Text #9

Max Range: 1.6027. Min Range: -1.6027

Max Act: 1.0627. Min Act: -0.0001

Data Index: 723643 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 1.6027. Min Range: -1.6027

Max Act: 1.0748. Min Act: -0.0001

Data Index: 739329 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 1.6027. Min Range: -1.6027

Max Act: 1.1374. Min Act: -0.0001

Data Index: 1075702 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 1.6027. Min Range: -1.6027

Max Act: 1.1366. Min Act: -0.0001

Data Index: 688635 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 1.6027. Min Range: -1.6027

Max Act: 1.0360. Min Act: -0.0001

Data Index: 742269 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 1.6027. Min Range: -1.6027

Max Act: 1.0289. Min Act: -0.0001

Data Index: 201722 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 1.6027. Min Range: -1.6027

Max Act: 1.0664. Min Act: -0.0001

Data Index: 375953 (C4 (Web Text))

Max Activating Token Index: 632

Text #16

Max Range: 1.6027. Min Range: -1.6027

Max Act: 1.0286. Min Act: -0.0001

Data Index: 535265 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 1.6027. Min Range: -1.6027

Max Act: 0.9907. Min Act: -0.0001

Data Index: 85322 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 1.6027. Min Range: -1.6027

Max Act: 1.0124. Min Act: -0.0001

Data Index: 660449 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 1.6027. Min Range: -1.6027

Max Act: 0.9518. Min Act: -0.0001

Data Index: 1162494 (C4 (Web Text))

Max Activating Token Index: 537