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

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

Neuron 2552 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.6851. Min Act: -0.0000

Data Index: 1399905 (Python Code)

Max Activating Token Index: 518

Text #1

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5914. Min Act: -0.0000

Data Index: 1373885 (Python Code)

Max Activating Token Index: 233

Text #2

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5239. Min Act: -0.0000

Data Index: 1561491 (Python Code)

Max Activating Token Index: 466

Text #3

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5228. Min Act: -0.0000

Data Index: 1465832 (Python Code)

Max Activating Token Index: 1012

Text #4

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5850. Min Act: -0.0000

Data Index: 537147 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5056. Min Act: -0.0000

Data Index: 1399184 (Python Code)

Max Activating Token Index: 331

Text #6

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.4412. Min Act: -0.0000

Data Index: 544231 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.4492. Min Act: -0.0000

Data Index: 1578730 (Python Code)

Max Activating Token Index: 436

Text #8

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.4671. Min Act: -0.0000

Data Index: 1392068 (Python Code)

Max Activating Token Index: 694

Text #9

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.4524. Min Act: -0.0000

Data Index: 1410734 (Python Code)

Max Activating Token Index: 128

Text #10

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.4179. Min Act: -0.0000

Data Index: 628404 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.4311. Min Act: -0.0000

Data Index: 1615544 (Python Code)

Max Activating Token Index: 509

Text #12

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.4236. Min Act: -0.0000

Data Index: 1542636 (Python Code)

Max Activating Token Index: 772

Text #13

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.4415. Min Act: -0.0000

Data Index: 713840 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.4212. Min Act: -0.0000

Data Index: 1505901 (Python Code)

Max Activating Token Index: 62

Text #15

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.4318. Min Act: -0.0000

Data Index: 259930 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.4274. Min Act: -0.0000

Data Index: 504708 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.4088. Min Act: -0.0000

Data Index: 166283 (C4 (Web Text))

Max Activating Token Index: 708

Text #18

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.4226. Min Act: -0.0000

Data Index: 1433182 (Python Code)

Max Activating Token Index: 192

Text #19

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.4080. Min Act: -0.0000

Data Index: 1402678 (Python Code)

Max Activating Token Index: 244