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

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

Neuron 3854 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: 0.7170. Min Range: -0.7170

Max Act: 0.7170. Min Act: -0.0000

Data Index: 169583 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.6778. Min Act: -0.0000

Data Index: 596257 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.6485. Min Act: -0.0000

Data Index: 1343418 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5857. Min Act: 0.0000

Data Index: 481884 (C4 (Web Text))

Max Activating Token Index: 513

Text #4

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.6047. Min Act: -0.0000

Data Index: 1120608 (C4 (Web Text))

Max Activating Token Index: 657

Text #5

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5662. Min Act: -0.0000

Data Index: 613958 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5657. Min Act: -0.0000

Data Index: 1244345 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5938. Min Act: -0.0000

Data Index: 729551 (C4 (Web Text))

Max Activating Token Index: 490

Text #8

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5701. Min Act: -0.0000

Data Index: 388395 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5724. Min Act: -0.0000

Data Index: 1108525 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5195. Min Act: -0.0000

Data Index: 639388 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5658. Min Act: -0.0000

Data Index: 707345 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5624. Min Act: -0.0000

Data Index: 1062634 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5413. Min Act: -0.0000

Data Index: 308416 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5434. Min Act: -0.0000

Data Index: 968077 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5255. Min Act: -0.0000

Data Index: 780973 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5478. Min Act: -0.0000

Data Index: 73341 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5473. Min Act: -0.0000

Data Index: 434130 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5211. Min Act: -0.0000

Data Index: 565004 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5173. Min Act: -0.0000

Data Index: 810367 (C4 (Web Text))

Max Activating Token Index: 537