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

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

Neuron 627 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.8406. Min Act: -0.0000

Data Index: 479951 (C4 (Web Text))

Max Activating Token Index: 776

Text #1

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.8178. Min Act: -0.0000

Data Index: 554945 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.7925. Min Act: -0.0000

Data Index: 741866 (C4 (Web Text))

Max Activating Token Index: 660

Text #3

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.6394. Min Act: -0.0000

Data Index: 1541801 (Python Code)

Max Activating Token Index: 112

Text #4

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.6681. Min Act: -0.0000

Data Index: 704588 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.6263. Min Act: -0.0000

Data Index: 1509866 (Python Code)

Max Activating Token Index: 593

Text #6

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.5855. Min Act: -0.0000

Data Index: 1447016 (Python Code)

Max Activating Token Index: 593

Text #7

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.5924. Min Act: -0.0000

Data Index: 1401783 (Python Code)

Max Activating Token Index: 133

Text #8

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.5763. Min Act: -0.0000

Data Index: 1452056 (Python Code)

Max Activating Token Index: 771

Text #9

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.5627. Min Act: -0.0000

Data Index: 115944 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.5615. Min Act: -0.0000

Data Index: 1464683 (Python Code)

Max Activating Token Index: 159

Text #11

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.5280. Min Act: -0.0000

Data Index: 1551924 (Python Code)

Max Activating Token Index: 623

Text #12

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.5910. Min Act: -0.0000

Data Index: 1469581 (Python Code)

Max Activating Token Index: 890

Text #13

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.5486. Min Act: -0.0000

Data Index: 1509798 (Python Code)

Max Activating Token Index: 799

Text #14

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.5453. Min Act: -0.0000

Data Index: 1254219 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.5978. Min Act: -0.0000

Data Index: 1018432 (C4 (Web Text))

Max Activating Token Index: 177

Text #16

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.5605. Min Act: -0.0000

Data Index: 761728 (C4 (Web Text))

Max Activating Token Index: 291

Text #17

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.5117. Min Act: -0.0000

Data Index: 948238 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.5045. Min Act: -0.0000

Data Index: 130927 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.5221. Min Act: -0.0000

Data Index: 1565723 (Python Code)

Max Activating Token Index: 206