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

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

Neuron 4725 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9313. Min Range: -2.9313

Max Act: 2.7697. Min Act: -0.0000

Data Index: 690846 (C4 (Web Text))

Max Activating Token Index: 376

Text #1

Max Range: 2.9313. Min Range: -2.9313

Max Act: 2.6865. Min Act: -0.0000

Data Index: 762691 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 2.9313. Min Range: -2.9313

Max Act: 2.9313. Min Act: -0.0000

Data Index: 525636 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 2.9313. Min Range: -2.9313

Max Act: 2.4119. Min Act: -0.0000

Data Index: 427565 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 2.9313. Min Range: -2.9313

Max Act: 2.6951. Min Act: -0.0000

Data Index: 229379 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 2.9313. Min Range: -2.9313

Max Act: 2.3570. Min Act: -0.0000

Data Index: 1444163 (Python Code)

Max Activating Token Index: 689

Text #6

Max Range: 2.9313. Min Range: -2.9313

Max Act: 2.0099. Min Act: -0.0000

Data Index: 681348 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 2.9313. Min Range: -2.9313

Max Act: 2.3355. Min Act: -0.0000

Data Index: 848785 (C4 (Web Text))

Max Activating Token Index: 505

Text #8

Max Range: 2.9313. Min Range: -2.9313

Max Act: 1.9418. Min Act: -0.0000

Data Index: 1341262 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 2.9313. Min Range: -2.9313

Max Act: 1.9316. Min Act: -0.0000

Data Index: 179259 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 2.9313. Min Range: -2.9313

Max Act: 2.1111. Min Act: -0.0000

Data Index: 1649249 (Python Code)

Max Activating Token Index: 373

Text #11

Max Range: 2.9313. Min Range: -2.9313

Max Act: 2.0931. Min Act: -0.0000

Data Index: 973810 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 2.9313. Min Range: -2.9313

Max Act: 2.2150. Min Act: -0.0000

Data Index: 496302 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 2.9313. Min Range: -2.9313

Max Act: 1.8657. Min Act: -0.0000

Data Index: 777128 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 2.9313. Min Range: -2.9313

Max Act: 1.7671. Min Act: -0.0000

Data Index: 599282 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 2.9313. Min Range: -2.9313

Max Act: 1.6798. Min Act: -0.0000

Data Index: 1117397 (C4 (Web Text))

Max Activating Token Index: 616

Text #16

Max Range: 2.9313. Min Range: -2.9313

Max Act: 1.6064. Min Act: -0.0000

Data Index: 1386994 (Python Code)

Max Activating Token Index: 759

Text #17

Max Range: 2.9313. Min Range: -2.9313

Max Act: 1.6074. Min Act: -0.0000

Data Index: 316223 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 2.9313. Min Range: -2.9313

Max Act: 1.6190. Min Act: -0.0000

Data Index: 178948 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 2.9313. Min Range: -2.9313

Max Act: 1.5682. Min Act: -0.0000

Data Index: 278362 (C4 (Web Text))

Max Activating Token Index: 764