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

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

Neuron 4604 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: 0.0506. Min Range: -0.0506

Max Act: 0.0506. Min Act: -0.0002

Data Index: 1034846 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0479. Min Act: -0.0002

Data Index: 201300 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0479. Min Act: -0.0002

Data Index: 1352922 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0488. Min Act: -0.0002

Data Index: 64039 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0456. Min Act: -0.0002

Data Index: 1085514 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0418. Min Act: -0.0002

Data Index: 187005 (C4 (Web Text))

Max Activating Token Index: 153

Text #6

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0453. Min Act: -0.0002

Data Index: 449225 (C4 (Web Text))

Max Activating Token Index: 222

Text #7

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0453. Min Act: -0.0002

Data Index: 533547 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0437. Min Act: -0.0002

Data Index: 1265143 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1287551 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0426. Min Act: -0.0002

Data Index: 543659 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0424. Min Act: -0.0002

Data Index: 139019 (C4 (Web Text))

Max Activating Token Index: 433

Text #12

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0437. Min Act: -0.0002

Data Index: 1106798 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0421. Min Act: -0.0002

Data Index: 369557 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0404. Min Act: -0.0002

Data Index: 87847 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0411. Min Act: -0.0002

Data Index: 94720 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0426. Min Act: -0.0002

Data Index: 377036 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0382. Min Act: -0.0002

Data Index: 1080878 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0385. Min Act: -0.0002

Data Index: 427182 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0405. Min Act: -0.0002

Data Index: 615643 (C4 (Web Text))

Max Activating Token Index: 511