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

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

Neuron 1106 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0369. Min Range: -2.0369

Max Act: 2.0369. Min Act: -0.0000

Data Index: 579687 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 2.0369. Min Range: -2.0369

Max Act: 1.9784. Min Act: -0.0000

Data Index: 615505 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 2.0369. Min Range: -2.0369

Max Act: 1.9213. Min Act: -0.0000

Data Index: 406034 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 2.0369. Min Range: -2.0369

Max Act: 1.8021. Min Act: -0.0000

Data Index: 709429 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 2.0369. Min Range: -2.0369

Max Act: 1.9038. Min Act: -0.0000

Data Index: 389768 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 2.0369. Min Range: -2.0369

Max Act: 1.9828. Min Act: -0.0000

Data Index: 255298 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 2.0369. Min Range: -2.0369

Max Act: 1.7711. Min Act: -0.0000

Data Index: 1215639 (C4 (Web Text))

Max Activating Token Index: 325

Text #7

Max Range: 2.0369. Min Range: -2.0369

Max Act: 1.9486. Min Act: -0.0000

Data Index: 629683 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 2.0369. Min Range: -2.0369

Max Act: 1.8908. Min Act: -0.0000

Data Index: 1315209 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 2.0369. Min Range: -2.0369

Max Act: 1.8379. Min Act: -0.0000

Data Index: 433414 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 2.0369. Min Range: -2.0369

Max Act: 1.5404. Min Act: -0.0000

Data Index: 473347 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 2.0369. Min Range: -2.0369

Max Act: 1.5139. Min Act: -0.0000

Data Index: 9059 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 2.0369. Min Range: -2.0369

Max Act: 1.4406. Min Act: -0.0000

Data Index: 1066709 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 2.0369. Min Range: -2.0369

Max Act: 1.4910. Min Act: -0.0000

Data Index: 1004860 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 2.0369. Min Range: -2.0369

Max Act: 1.4898. Min Act: -0.0000

Data Index: 548669 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 2.0369. Min Range: -2.0369

Max Act: 1.5499. Min Act: -0.0000

Data Index: 1158084 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 2.0369. Min Range: -2.0369

Max Act: 1.5334. Min Act: -0.0000

Data Index: 870352 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 2.0369. Min Range: -2.0369

Max Act: 1.5231. Min Act: -0.0000

Data Index: 552615 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 2.0369. Min Range: -2.0369

Max Act: 1.4198. Min Act: -0.0000

Data Index: 482200 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 2.0369. Min Range: -2.0369

Max Act: 1.5109. Min Act: -0.0000

Data Index: 350561 (C4 (Web Text))

Max Activating Token Index: 761