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

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

Neuron 962 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4570. Min Range: -1.4570

Max Act: 1.4570. Min Act: -0.0000

Data Index: 1539167 (Python Code)

Max Activating Token Index: 245

Text #1

Max Range: 1.4570. Min Range: -1.4570

Max Act: 1.1501. Min Act: -0.0000

Data Index: 536643 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 1.4570. Min Range: -1.4570

Max Act: 1.1343. Min Act: -0.0000

Data Index: 1346051 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 1.4570. Min Range: -1.4570

Max Act: 0.9899. Min Act: -0.0000

Data Index: 241375 (C4 (Web Text))

Max Activating Token Index: 404

Text #4

Max Range: 1.4570. Min Range: -1.4570

Max Act: 1.0999. Min Act: -0.0000

Data Index: 6185 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 1.4570. Min Range: -1.4570

Max Act: 1.1400. Min Act: -0.0000

Data Index: 439810 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 1.4570. Min Range: -1.4570

Max Act: 1.0704. Min Act: -0.0000

Data Index: 1244516 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 1.4570. Min Range: -1.4570

Max Act: 1.0234. Min Act: -0.0000

Data Index: 866511 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 1.4570. Min Range: -1.4570

Max Act: 0.9620. Min Act: -0.0000

Data Index: 285513 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 1.4570. Min Range: -1.4570

Max Act: 0.9260. Min Act: -0.0000

Data Index: 1032113 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 1.4570. Min Range: -1.4570

Max Act: 0.9294. Min Act: -0.0000

Data Index: 990316 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 1.4570. Min Range: -1.4570

Max Act: 1.0078. Min Act: -0.0000

Data Index: 344836 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 1.4570. Min Range: -1.4570

Max Act: 0.8800. Min Act: -0.0000

Data Index: 1420673 (Python Code)

Max Activating Token Index: 924

Text #13

Max Range: 1.4570. Min Range: -1.4570

Max Act: 0.9793. Min Act: -0.0000

Data Index: 1616864 (Python Code)

Max Activating Token Index: 444

Text #14

Max Range: 1.4570. Min Range: -1.4570

Max Act: 0.9271. Min Act: -0.0000

Data Index: 269577 (C4 (Web Text))

Max Activating Token Index: 865

Text #15

Max Range: 1.4570. Min Range: -1.4570

Max Act: 0.9358. Min Act: -0.0000

Data Index: 727868 (C4 (Web Text))

Max Activating Token Index: 445

Text #16

Max Range: 1.4570. Min Range: -1.4570

Max Act: 0.8791. Min Act: -0.0000

Data Index: 546515 (C4 (Web Text))

Max Activating Token Index: 542

Text #17

Max Range: 1.4570. Min Range: -1.4570

Max Act: 0.8979. Min Act: -0.0000

Data Index: 1571695 (Python Code)

Max Activating Token Index: 975

Text #18

Max Range: 1.4570. Min Range: -1.4570

Max Act: 0.9255. Min Act: -0.0000

Data Index: 246871 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 1.4570. Min Range: -1.4570

Max Act: 0.9268. Min Act: -0.0000

Data Index: 1227626 (C4 (Web Text))

Max Activating Token Index: 693