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

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

Neuron 2003 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0570. Min Act: -0.0002

Data Index: 348230 (C4 (Web Text))

Max Activating Token Index: 642

Text #1

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0507. Min Act: -0.0002

Data Index: 193360 (C4 (Web Text))

Max Activating Token Index: 712

Text #2

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0511. Min Act: -0.0001

Data Index: 324124 (C4 (Web Text))

Max Activating Token Index: 446

Text #3

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0464. Min Act: -0.0002

Data Index: 737169 (C4 (Web Text))

Max Activating Token Index: 486

Text #4

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0500. Min Act: -0.0002

Data Index: 685769 (C4 (Web Text))

Max Activating Token Index: 898

Text #5

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0606. Min Act: -0.0001

Data Index: 109041 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0474. Min Act: -0.0002

Data Index: 983539 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0434. Min Act: -0.0001

Data Index: 812607 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0448. Min Act: -0.0001

Data Index: 1195415 (C4 (Web Text))

Max Activating Token Index: 984

Text #9

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0429. Min Act: -0.0001

Data Index: 1295245 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0427. Min Act: -0.0001

Data Index: 897234 (C4 (Web Text))

Max Activating Token Index: 611

Text #11

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0384. Min Act: -0.0001

Data Index: 1315129 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0425. Min Act: -0.0001

Data Index: 468861 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0385. Min Act: -0.0001

Data Index: 1028891 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0461. Min Act: -0.0001

Data Index: 145177 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0444. Min Act: -0.0001

Data Index: 654150 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0436. Min Act: -0.0001

Data Index: 377033 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0434. Min Act: -0.0002

Data Index: 641885 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0394. Min Act: -0.0002

Data Index: 902025 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0420. Min Act: -0.0001

Data Index: 1169255 (C4 (Web Text))

Max Activating Token Index: 447