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

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

Neuron 2789 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3534. Min Range: -2.3534

Max Act: 2.3534. Min Act: -0.0000

Data Index: 390202 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 2.3534. Min Range: -2.3534

Max Act: 2.2340. Min Act: -0.0000

Data Index: 335738 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 2.3534. Min Range: -2.3534

Max Act: 1.8086. Min Act: -0.0000

Data Index: 82820 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 2.3534. Min Range: -2.3534

Max Act: 1.7561. Min Act: -0.0000

Data Index: 209597 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 2.3534. Min Range: -2.3534

Max Act: 1.4362. Min Act: -0.0000

Data Index: 978549 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 2.3534. Min Range: -2.3534

Max Act: 1.5229. Min Act: -0.0000

Data Index: 462436 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 2.3534. Min Range: -2.3534

Max Act: 1.4591. Min Act: -0.0000

Data Index: 418265 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 2.3534. Min Range: -2.3534

Max Act: 1.3603. Min Act: -0.0000

Data Index: 588263 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 2.3534. Min Range: -2.3534

Max Act: 1.1673. Min Act: -0.0000

Data Index: 1306800 (C4 (Web Text))

Max Activating Token Index: 337

Text #9

Max Range: 2.3534. Min Range: -2.3534

Max Act: 1.3557. Min Act: -0.0000

Data Index: 173337 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 2.3534. Min Range: -2.3534

Max Act: 1.3201. Min Act: -0.0000

Data Index: 94834 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 2.3534. Min Range: -2.3534

Max Act: 1.3995. Min Act: -0.0000

Data Index: 110390 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 2.3534. Min Range: -2.3534

Max Act: 1.2809. Min Act: -0.0000

Data Index: 26453 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 2.3534. Min Range: -2.3534

Max Act: 1.3410. Min Act: -0.0000

Data Index: 27417 (C4 (Web Text))

Max Activating Token Index: 402

Text #14

Max Range: 2.3534. Min Range: -2.3534

Max Act: 1.3365. Min Act: -0.0000

Data Index: 328914 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 2.3534. Min Range: -2.3534

Max Act: 1.1691. Min Act: -0.0000

Data Index: 405641 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 2.3534. Min Range: -2.3534

Max Act: 1.2128. Min Act: -0.0000

Data Index: 841930 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 2.3534. Min Range: -2.3534

Max Act: 1.2006. Min Act: -0.0000

Data Index: 673913 (C4 (Web Text))

Max Activating Token Index: 244

Text #18

Max Range: 2.3534. Min Range: -2.3534

Max Act: 1.1963. Min Act: -0.0000

Data Index: 636135 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 2.3534. Min Range: -2.3534

Max Act: 1.1990. Min Act: -0.0000

Data Index: 804350 (C4 (Web Text))

Max Activating Token Index: 663