Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4270 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.4662. Min Act: -0.0000

Data Index: 245968 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.4164. Min Act: -0.0000

Data Index: 309186 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3588. Min Act: -0.0000

Data Index: 138616 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3315. Min Act: -0.0000

Data Index: 169775 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3561. Min Act: -0.0000

Data Index: 68018 (C4 (Web Text))

Max Activating Token Index: 611

Text #5

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3344. Min Act: -0.0000

Data Index: 453906 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3257. Min Act: -0.0000

Data Index: 138129 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3246. Min Act: -0.0000

Data Index: 1515962 (Python Code)

Max Activating Token Index: 752

Text #8

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3272. Min Act: -0.0000

Data Index: 1172071 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3044. Min Act: -0.0000

Data Index: 1050343 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3298. Min Act: -0.0000

Data Index: 358912 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3465. Min Act: -0.0000

Data Index: 343098 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.2938. Min Act: -0.0000

Data Index: 452363 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.2919. Min Act: -0.0000

Data Index: 731400 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.2974. Min Act: -0.0000

Data Index: 1010314 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.2763. Min Act: -0.0000

Data Index: 253848 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3028. Min Act: -0.0000

Data Index: 253154 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.2847. Min Act: -0.0000

Data Index: 1091452 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.2991. Min Act: -0.0000

Data Index: 1050929 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.2679. Min Act: -0.0000

Data Index: 1083414 (C4 (Web Text))

Max Activating Token Index: 879