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

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

Neuron 3954 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0705. Min Act: -0.0002

Data Index: 50263 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0526. Min Act: -0.0002

Data Index: 265548 (C4 (Web Text))

Max Activating Token Index: 275

Text #2

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0508. Min Act: -0.0002

Data Index: 85030 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0478. Min Act: -0.0002

Data Index: 902637 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0482. Min Act: -0.0002

Data Index: 1234851 (C4 (Web Text))

Max Activating Token Index: 985

Text #5

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0493. Min Act: -0.0002

Data Index: 1291454 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0455. Min Act: -0.0002

Data Index: 242232 (C4 (Web Text))

Max Activating Token Index: 668

Text #7

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0447. Min Act: -0.0002

Data Index: 475702 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0427. Min Act: -0.0002

Data Index: 59418 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0460. Min Act: -0.0002

Data Index: 743759 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0427. Min Act: -0.0002

Data Index: 169994 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0435. Min Act: -0.0002

Data Index: 363659 (C4 (Web Text))

Max Activating Token Index: 203

Text #12

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0431. Min Act: -0.0002

Data Index: 118366 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0447. Min Act: -0.0002

Data Index: 620098 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0437. Min Act: -0.0002

Data Index: 43231 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0440. Min Act: -0.0002

Data Index: 497472 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0426. Min Act: -0.0002

Data Index: 702993 (C4 (Web Text))

Max Activating Token Index: 501

Text #17

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0398. Min Act: -0.0002

Data Index: 4176 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0421. Min Act: -0.0002

Data Index: 1002755 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0420. Min Act: -0.0002

Data Index: 424620 (C4 (Web Text))

Max Activating Token Index: 518