Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1852 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1965. Min Act: -0.0005

Data Index: 163676 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1870. Min Act: -0.0005

Data Index: 1220674 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1691. Min Act: -0.0005

Data Index: 519857 (C4 (Web Text))

Max Activating Token Index: 899

Text #3

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1772. Min Act: -0.0005

Data Index: 574872 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1651. Min Act: -0.0005

Data Index: 134131 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1439. Min Act: -0.0005

Data Index: 920336 (C4 (Web Text))

Max Activating Token Index: 515

Text #6

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1419. Min Act: -0.0005

Data Index: 668641 (C4 (Web Text))

Max Activating Token Index: 883

Text #7

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1387. Min Act: -0.0005

Data Index: 575495 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1372. Min Act: -0.0005

Data Index: 47387 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1348. Min Act: -0.0005

Data Index: 104752 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1395. Min Act: -0.0005

Data Index: 654234 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1333. Min Act: -0.0004

Data Index: 1345818 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1277. Min Act: -0.0005

Data Index: 323880 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1324. Min Act: -0.0005

Data Index: 147095 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1321. Min Act: -0.0005

Data Index: 322323 (C4 (Web Text))

Max Activating Token Index: 596

Text #15

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1279. Min Act: -0.0005

Data Index: 82892 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1219. Min Act: -0.0005

Data Index: 927103 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1099. Min Act: -0.0005

Data Index: 448942 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1210. Min Act: -0.0005

Data Index: 186111 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1214. Min Act: -0.0005

Data Index: 337888 (C4 (Web Text))

Max Activating Token Index: 953