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

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

Neuron 1445 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4754. Min Range: -1.4754

Max Act: 1.3389. Min Act: -0.0001

Data Index: 574300 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 1.4754. Min Range: -1.4754

Max Act: 1.3971. Min Act: -0.0001

Data Index: 640218 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 1.4754. Min Range: -1.4754

Max Act: 1.3939. Min Act: -0.0001

Data Index: 818577 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 1.4754. Min Range: -1.4754

Max Act: 1.3442. Min Act: -0.0001

Data Index: 1013259 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 1.4754. Min Range: -1.4754

Max Act: 1.1203. Min Act: -0.0001

Data Index: 638365 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 1.4754. Min Range: -1.4754

Max Act: 1.2973. Min Act: -0.0001

Data Index: 774490 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 1.4754. Min Range: -1.4754

Max Act: 1.4652. Min Act: -0.0001

Data Index: 1188795 (C4 (Web Text))

Max Activating Token Index: 781

Text #7

Max Range: 1.4754. Min Range: -1.4754

Max Act: 1.2601. Min Act: -0.0001

Data Index: 910369 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 1.4754. Min Range: -1.4754

Max Act: 1.4754. Min Act: -0.0001

Data Index: 1279524 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 1.4754. Min Range: -1.4754

Max Act: 1.3489. Min Act: -0.0001

Data Index: 1054729 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 1.4754. Min Range: -1.4754

Max Act: 1.1302. Min Act: -0.0001

Data Index: 910779 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 1.4754. Min Range: -1.4754

Max Act: 1.3847. Min Act: -0.0001

Data Index: 162016 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 1.4754. Min Range: -1.4754

Max Act: 1.2811. Min Act: -0.0001

Data Index: 669637 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 1.4754. Min Range: -1.4754

Max Act: 1.1575. Min Act: -0.0001

Data Index: 862553 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 1.4754. Min Range: -1.4754

Max Act: 1.1499. Min Act: -0.0001

Data Index: 818940 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 1.4754. Min Range: -1.4754

Max Act: 1.1412. Min Act: -0.0001

Data Index: 1313306 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 1.4754. Min Range: -1.4754

Max Act: 1.0907. Min Act: -0.0001

Data Index: 1086098 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 1.4754. Min Range: -1.4754

Max Act: 1.2183. Min Act: -0.0001

Data Index: 206944 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 1.4754. Min Range: -1.4754

Max Act: 1.1278. Min Act: -0.0001

Data Index: 146590 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 1.4754. Min Range: -1.4754

Max Act: 1.1239. Min Act: -0.0001

Data Index: 1215854 (C4 (Web Text))

Max Activating Token Index: 746