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

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

Neuron 2006 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.9536. Min Range: -1.9536

Max Act: 1.9536. Min Act: -0.0002

Data Index: 1603776 (Python Code)

Max Activating Token Index: 114

Text #1

Max Range: 1.9536. Min Range: -1.9536

Max Act: 1.8419. Min Act: -0.0002

Data Index: 1011941 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 1.9536. Min Range: -1.9536

Max Act: 1.8598. Min Act: -0.0002

Data Index: 703400 (C4 (Web Text))

Max Activating Token Index: 840

Text #3

Max Range: 1.9536. Min Range: -1.9536

Max Act: 1.8223. Min Act: -0.0002

Data Index: 1302207 (C4 (Web Text))

Max Activating Token Index: 637

Text #4

Max Range: 1.9536. Min Range: -1.9536

Max Act: 1.7406. Min Act: -0.0002

Data Index: 94503 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 1.9536. Min Range: -1.9536

Max Act: 1.7437. Min Act: -0.0002

Data Index: 320782 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 1.9536. Min Range: -1.9536

Max Act: 1.7607. Min Act: -0.0002

Data Index: 706367 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 1.9536. Min Range: -1.9536

Max Act: 1.7797. Min Act: -0.0002

Data Index: 123837 (C4 (Web Text))

Max Activating Token Index: 719

Text #8

Max Range: 1.9536. Min Range: -1.9536

Max Act: 1.7420. Min Act: -0.0002

Data Index: 590376 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 1.9536. Min Range: -1.9536

Max Act: 1.7217. Min Act: -0.0002

Data Index: 1109025 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 1.9536. Min Range: -1.9536

Max Act: 1.7319. Min Act: -0.0002

Data Index: 1071912 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 1.9536. Min Range: -1.9536

Max Act: 1.6629. Min Act: -0.0002

Data Index: 416167 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 1.9536. Min Range: -1.9536

Max Act: 1.6967. Min Act: -0.0002

Data Index: 687560 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 1.9536. Min Range: -1.9536

Max Act: 1.6786. Min Act: -0.0002

Data Index: 940458 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 1.9536. Min Range: -1.9536

Max Act: 1.6393. Min Act: -0.0002

Data Index: 627976 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 1.9536. Min Range: -1.9536

Max Act: 1.7566. Min Act: -0.0002

Data Index: 923538 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 1.9536. Min Range: -1.9536

Max Act: 1.6872. Min Act: -0.0002

Data Index: 655497 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 1.9536. Min Range: -1.9536

Max Act: 1.6410. Min Act: -0.0002

Data Index: 380456 (C4 (Web Text))

Max Activating Token Index: 615

Text #18

Max Range: 1.9536. Min Range: -1.9536

Max Act: 1.7200. Min Act: -0.0002

Data Index: 1220274 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 1.9536. Min Range: -1.9536

Max Act: 1.6709. Min Act: -0.0002

Data Index: 1317742 (C4 (Web Text))

Max Activating Token Index: 835