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

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

Neuron 3725 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4286. Min Range: -0.4286

Max Act: 0.4286. Min Act: -0.0000

Data Index: 730678 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 0.4286. Min Range: -0.4286

Max Act: 0.4139. Min Act: -0.0000

Data Index: 1339160 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 0.4286. Min Range: -0.4286

Max Act: 0.4265. Min Act: -0.0000

Data Index: 45714 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 0.4286. Min Range: -0.4286

Max Act: 0.3846. Min Act: -0.0000

Data Index: 1333772 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 0.4286. Min Range: -0.4286

Max Act: 0.3789. Min Act: -0.0000

Data Index: 740001 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 0.4286. Min Range: -0.4286

Max Act: 0.3579. Min Act: -0.0000

Data Index: 1297179 (C4 (Web Text))

Max Activating Token Index: 415

Text #6

Max Range: 0.4286. Min Range: -0.4286

Max Act: 0.3850. Min Act: -0.0000

Data Index: 1116755 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 0.4286. Min Range: -0.4286

Max Act: 0.3749. Min Act: -0.0000

Data Index: 271000 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 0.4286. Min Range: -0.4286

Max Act: 0.3132. Min Act: -0.0000

Data Index: 336629 (C4 (Web Text))

Max Activating Token Index: 397

Text #9

Max Range: 0.4286. Min Range: -0.4286

Max Act: 0.3555. Min Act: -0.0000

Data Index: 562794 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 0.4286. Min Range: -0.4286

Max Act: 0.3918. Min Act: -0.0000

Data Index: 65233 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 0.4286. Min Range: -0.4286

Max Act: 0.3545. Min Act: -0.0000

Data Index: 574146 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 0.4286. Min Range: -0.4286

Max Act: 0.3551. Min Act: -0.0000

Data Index: 560176 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 0.4286. Min Range: -0.4286

Max Act: 0.3639. Min Act: -0.0000

Data Index: 69517 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 0.4286. Min Range: -0.4286

Max Act: 0.3348. Min Act: -0.0000

Data Index: 1293751 (C4 (Web Text))

Max Activating Token Index: 300

Text #15

Max Range: 0.4286. Min Range: -0.4286

Max Act: 0.3579. Min Act: -0.0000

Data Index: 572454 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 0.4286. Min Range: -0.4286

Max Act: 0.3683. Min Act: -0.0000

Data Index: 818299 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 0.4286. Min Range: -0.4286

Max Act: 0.3396. Min Act: -0.0000

Data Index: 621385 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 0.4286. Min Range: -0.4286

Max Act: 0.3494. Min Act: -0.0000

Data Index: 1220966 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 0.4286. Min Range: -0.4286

Max Act: 0.3503. Min Act: -0.0000

Data Index: 584654 (C4 (Web Text))

Max Activating Token Index: 171