Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5549 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.0351. Min Range: -6.0351

Max Act: 6.0351. Min Act: -0.0000

Data Index: 286209 (C4 (Web Text))

Max Activating Token Index: 650

Text #1

Max Range: 6.0351. Min Range: -6.0351

Max Act: 5.9120. Min Act: -0.0000

Data Index: 1116507 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 6.0351. Min Range: -6.0351

Max Act: 5.3705. Min Act: -0.0000

Data Index: 482187 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 6.0351. Min Range: -6.0351

Max Act: 5.5880. Min Act: -0.0000

Data Index: 248716 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 6.0351. Min Range: -6.0351

Max Act: 5.5295. Min Act: -0.0000

Data Index: 997607 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 6.0351. Min Range: -6.0351

Max Act: 5.3393. Min Act: -0.0000

Data Index: 1252713 (C4 (Web Text))

Max Activating Token Index: 282

Text #6

Max Range: 6.0351. Min Range: -6.0351

Max Act: 5.3625. Min Act: -0.0000

Data Index: 1202219 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 6.0351. Min Range: -6.0351

Max Act: 5.0295. Min Act: -0.0000

Data Index: 384322 (C4 (Web Text))

Max Activating Token Index: 660

Text #8

Max Range: 6.0351. Min Range: -6.0351

Max Act: 5.3096. Min Act: -0.0000

Data Index: 824462 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 6.0351. Min Range: -6.0351

Max Act: 5.2414. Min Act: -0.0000

Data Index: 584398 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 6.0351. Min Range: -6.0351

Max Act: 4.9592. Min Act: -0.0000

Data Index: 1274727 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 6.0351. Min Range: -6.0351

Max Act: 5.1384. Min Act: -0.0000

Data Index: 152759 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 6.0351. Min Range: -6.0351

Max Act: 5.0536. Min Act: -0.0000

Data Index: 606891 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 6.0351. Min Range: -6.0351

Max Act: 4.6846. Min Act: -0.0000

Data Index: 1517141 (Python Code)

Max Activating Token Index: 65

Text #14

Max Range: 6.0351. Min Range: -6.0351

Max Act: 4.8947. Min Act: -0.0000

Data Index: 871631 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 6.0351. Min Range: -6.0351

Max Act: 5.0191. Min Act: -0.0000

Data Index: 1157261 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 6.0351. Min Range: -6.0351

Max Act: 4.7397. Min Act: -0.0000

Data Index: 818503 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 6.0351. Min Range: -6.0351

Max Act: 4.7310. Min Act: -0.0000

Data Index: 227329 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 6.0351. Min Range: -6.0351

Max Act: 4.7262. Min Act: -0.0000

Data Index: 1157740 (C4 (Web Text))

Max Activating Token Index: 429

Text #19

Max Range: 6.0351. Min Range: -6.0351

Max Act: 4.5197. Min Act: -0.0000

Data Index: 631906 (C4 (Web Text))

Max Activating Token Index: 292