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

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

Neuron 2125 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8277. Min Range: -1.8277

Max Act: 1.8277. Min Act: -0.0000

Data Index: 740203 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 1.8277. Min Range: -1.8277

Max Act: 1.8079. Min Act: -0.0000

Data Index: 1090643 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 1.8277. Min Range: -1.8277

Max Act: 1.6331. Min Act: -0.0000

Data Index: 47490 (C4 (Web Text))

Max Activating Token Index: 984

Text #3

Max Range: 1.8277. Min Range: -1.8277

Max Act: 1.6169. Min Act: -0.0000

Data Index: 1337427 (C4 (Web Text))

Max Activating Token Index: 757

Text #4

Max Range: 1.8277. Min Range: -1.8277

Max Act: 1.4684. Min Act: -0.0000

Data Index: 1052463 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 1.8277. Min Range: -1.8277

Max Act: 1.4881. Min Act: -0.0000

Data Index: 257662 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 1.8277. Min Range: -1.8277

Max Act: 1.4358. Min Act: -0.0000

Data Index: 1427660 (Python Code)

Max Activating Token Index: 794

Text #7

Max Range: 1.8277. Min Range: -1.8277

Max Act: 1.5627. Min Act: -0.0000

Data Index: 186841 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 1.8277. Min Range: -1.8277

Max Act: 1.4663. Min Act: -0.0000

Data Index: 1392970 (Python Code)

Max Activating Token Index: 275

Text #9

Max Range: 1.8277. Min Range: -1.8277

Max Act: 1.4332. Min Act: -0.0000

Data Index: 649111 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 1.8277. Min Range: -1.8277

Max Act: 1.5106. Min Act: -0.0000

Data Index: 1008702 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 1.8277. Min Range: -1.8277

Max Act: 1.3457. Min Act: -0.0000

Data Index: 555464 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 1.8277. Min Range: -1.8277

Max Act: 1.3475. Min Act: -0.0000

Data Index: 521253 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 1.8277. Min Range: -1.8277

Max Act: 1.4490. Min Act: -0.0000

Data Index: 227411 (C4 (Web Text))

Max Activating Token Index: 555

Text #14

Max Range: 1.8277. Min Range: -1.8277

Max Act: 1.3527. Min Act: -0.0000

Data Index: 511364 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 1.8277. Min Range: -1.8277

Max Act: 1.4244. Min Act: -0.0000

Data Index: 1109705 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 1.8277. Min Range: -1.8277

Max Act: 1.2617. Min Act: -0.0000

Data Index: 862482 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 1.8277. Min Range: -1.8277

Max Act: 1.2200. Min Act: -0.0000

Data Index: 1368368 (Python Code)

Max Activating Token Index: 719

Text #18

Max Range: 1.8277. Min Range: -1.8277

Max Act: 1.3315. Min Act: -0.0000

Data Index: 1300497 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 1.8277. Min Range: -1.8277

Max Act: 1.3191. Min Act: -0.0000

Data Index: 1268209 (C4 (Web Text))

Max Activating Token Index: 494