Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1125 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0487. Min Act: -0.0002

Data Index: 974528 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0435. Min Act: -0.0003

Data Index: 1067975 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0432. Min Act: -0.0003

Data Index: 1098670 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0422. Min Act: -0.0003

Data Index: 247895 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0416. Min Act: -0.0003

Data Index: 1483188 (Python Code)

Max Activating Token Index: 25

Text #5

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0423. Min Act: -0.0003

Data Index: 888608 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0436. Min Act: -0.0003

Data Index: 1317565 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0419. Min Act: -0.0003

Data Index: 553878 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0412. Min Act: -0.0002

Data Index: 156825 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0404. Min Act: -0.0002

Data Index: 452967 (C4 (Web Text))

Max Activating Token Index: 239

Text #10

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0391. Min Act: -0.0003

Data Index: 1111827 (C4 (Web Text))

Max Activating Token Index: 396

Text #11

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0397. Min Act: -0.0003

Data Index: 936664 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0409. Min Act: -0.0003

Data Index: 208631 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0397. Min Act: -0.0002

Data Index: 1356084 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0400. Min Act: -0.0003

Data Index: 537429 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0398. Min Act: -0.0003

Data Index: 1202390 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0408. Min Act: -0.0003

Data Index: 1172225 (C4 (Web Text))

Max Activating Token Index: 234

Text #17

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0389. Min Act: -0.0003

Data Index: 1390165 (Python Code)

Max Activating Token Index: 361

Text #18

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0382. Min Act: -0.0002

Data Index: 283686 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0375. Min Act: -0.0003

Data Index: 1056518 (C4 (Web Text))

Max Activating Token Index: 408