Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2550 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.5871. Min Act: -0.0000

Data Index: 1285359 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.6219. Min Act: -0.0000

Data Index: 1084675 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.6180. Min Act: -0.0001

Data Index: 960996 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.6085. Min Act: -0.0001

Data Index: 341067 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.5504. Min Act: -0.0000

Data Index: 327734 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.5312. Min Act: -0.0001

Data Index: 1277221 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.5828. Min Act: -0.0000

Data Index: 647413 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.5091. Min Act: -0.0000

Data Index: 928377 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.5407. Min Act: -0.0000

Data Index: 567458 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.5270. Min Act: -0.0001

Data Index: 445325 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.4981. Min Act: -0.0001

Data Index: 1093647 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.5151. Min Act: -0.0000

Data Index: 1163212 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.4754. Min Act: -0.0000

Data Index: 533436 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.4692. Min Act: -0.0001

Data Index: 404425 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.4508. Min Act: -0.0000

Data Index: 47492 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.4338. Min Act: -0.0001

Data Index: 1305929 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.4614. Min Act: -0.0000

Data Index: 1239803 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.4314. Min Act: -0.0000

Data Index: 85721 (C4 (Web Text))

Max Activating Token Index: 629

Text #18

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.4252. Min Act: -0.0000

Data Index: 614525 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.4385. Min Act: -0.0000

Data Index: 1046087 (C4 (Web Text))

Max Activating Token Index: 404