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

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

Neuron 4974 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.8341. Min Act: -0.0000

Data Index: 1485368 (Python Code)

Max Activating Token Index: 630

Text #1

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.7775. Min Act: -0.0000

Data Index: 722251 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.7398. Min Act: -0.0000

Data Index: 1072924 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.6532. Min Act: -0.0000

Data Index: 1594855 (Python Code)

Max Activating Token Index: 346

Text #4

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.6515. Min Act: -0.0000

Data Index: 1476922 (Python Code)

Max Activating Token Index: 511

Text #5

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.5481. Min Act: -0.0000

Data Index: 1102340 (C4 (Web Text))

Max Activating Token Index: 955

Text #6

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.6351. Min Act: 0.0000

Data Index: 683910 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.4520. Min Act: -0.0000

Data Index: 1409178 (Python Code)

Max Activating Token Index: 388

Text #8

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.5079. Min Act: -0.0000

Data Index: 1592963 (Python Code)

Max Activating Token Index: 603

Text #9

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.6878. Min Act: -0.0000

Data Index: 111699 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.5716. Min Act: 0.0000

Data Index: 1102984 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.5719. Min Act: -0.0000

Data Index: 1365518 (Python Code)

Max Activating Token Index: 479

Text #12

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.5480. Min Act: -0.0000

Data Index: 1035171 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.5591. Min Act: 0.0000

Data Index: 799581 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.6216. Min Act: -0.0000

Data Index: 1600444 (Python Code)

Max Activating Token Index: 458

Text #15

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.5597. Min Act: -0.0000

Data Index: 1293598 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.5501. Min Act: -0.0000

Data Index: 1230489 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.5283. Min Act: -0.0000

Data Index: 642713 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.4440. Min Act: -0.0000

Data Index: 1627867 (Python Code)

Max Activating Token Index: 163

Text #19

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.3708. Min Act: -0.0000

Data Index: 1473660 (Python Code)

Max Activating Token Index: 654