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

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

Neuron 3986 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2787. Min Range: -1.2787

Max Act: 1.2787. Min Act: -0.0000

Data Index: 1098313 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 1.2787. Min Range: -1.2787

Max Act: 1.0163. Min Act: -0.0000

Data Index: 618386 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 1.2787. Min Range: -1.2787

Max Act: 0.8316. Min Act: -0.0000

Data Index: 546363 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 1.2787. Min Range: -1.2787

Max Act: 0.8211. Min Act: -0.0000

Data Index: 470764 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 1.2787. Min Range: -1.2787

Max Act: 0.8400. Min Act: -0.0000

Data Index: 1275576 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 1.2787. Min Range: -1.2787

Max Act: 0.7542. Min Act: -0.0001

Data Index: 824777 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 1.2787. Min Range: -1.2787

Max Act: 0.7469. Min Act: -0.0000

Data Index: 1049189 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 1.2787. Min Range: -1.2787

Max Act: 0.7318. Min Act: -0.0000

Data Index: 1303426 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 1.2787. Min Range: -1.2787

Max Act: 0.7283. Min Act: -0.0000

Data Index: 1089679 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 1.2787. Min Range: -1.2787

Max Act: 0.7202. Min Act: -0.0001

Data Index: 935037 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 1.2787. Min Range: -1.2787

Max Act: 0.6889. Min Act: -0.0000

Data Index: 966992 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 1.2787. Min Range: -1.2787

Max Act: 0.7315. Min Act: -0.0000

Data Index: 602740 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 1.2787. Min Range: -1.2787

Max Act: 0.6677. Min Act: -0.0000

Data Index: 575058 (C4 (Web Text))

Max Activating Token Index: 766

Text #13

Max Range: 1.2787. Min Range: -1.2787

Max Act: 0.6536. Min Act: -0.0000

Data Index: 1244264 (C4 (Web Text))

Max Activating Token Index: 512

Text #14

Max Range: 1.2787. Min Range: -1.2787

Max Act: 0.6868. Min Act: -0.0000

Data Index: 339308 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 1.2787. Min Range: -1.2787

Max Act: 0.6608. Min Act: -0.0000

Data Index: 969213 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 1.2787. Min Range: -1.2787

Max Act: 0.6598. Min Act: -0.0000

Data Index: 1228732 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 1.2787. Min Range: -1.2787

Max Act: 0.6546. Min Act: -0.0000

Data Index: 543895 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 1.2787. Min Range: -1.2787

Max Act: 0.6511. Min Act: -0.0000

Data Index: 83224 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 1.2787. Min Range: -1.2787

Max Act: 0.6719. Min Act: -0.0000

Data Index: 547983 (C4 (Web Text))

Max Activating Token Index: 866