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

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

Neuron 3403 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: 0.8428. Min Range: -0.8428

Max Act: 0.8428. Min Act: -0.0001

Data Index: 68643 (C4 (Web Text))

Max Activating Token Index: 365

Text #1

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.7501. Min Act: -0.0001

Data Index: 712658 (C4 (Web Text))

Max Activating Token Index: 776

Text #2

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.7054. Min Act: -0.0001

Data Index: 1552418 (Python Code)

Max Activating Token Index: 448

Text #3

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.7227. Min Act: -0.0001

Data Index: 247464 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.6852. Min Act: -0.0002

Data Index: 1003351 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.6776. Min Act: -0.0001

Data Index: 1387724 (Python Code)

Max Activating Token Index: 510

Text #6

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.6372. Min Act: -0.0001

Data Index: 460089 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.6349. Min Act: -0.0001

Data Index: 609774 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.6292. Min Act: -0.0002

Data Index: 936751 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.6205. Min Act: -0.0001

Data Index: 469492 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.6146. Min Act: -0.0001

Data Index: 1433588 (Python Code)

Max Activating Token Index: 854

Text #11

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.6316. Min Act: -0.0002

Data Index: 216310 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.5969. Min Act: -0.0001

Data Index: 995734 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.6203. Min Act: -0.0002

Data Index: 265871 (C4 (Web Text))

Max Activating Token Index: 144

Text #14

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.6326. Min Act: -0.0002

Data Index: 639991 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.5907. Min Act: -0.0002

Data Index: 226812 (C4 (Web Text))

Max Activating Token Index: 431

Text #16

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.6049. Min Act: -0.0001

Data Index: 1410439 (Python Code)

Max Activating Token Index: 109

Text #17

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.6271. Min Act: -0.0002

Data Index: 814490 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.6075. Min Act: -0.0001

Data Index: 1568436 (Python Code)

Max Activating Token Index: 762

Text #19

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.6078. Min Act: -0.0001

Data Index: 974916 (C4 (Web Text))

Max Activating Token Index: 22