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

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

Neuron 4850 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5619. Min Range: -1.5619

Max Act: 1.5619. Min Act: -0.0000

Data Index: 1026011 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 1.5619. Min Range: -1.5619

Max Act: 1.4068. Min Act: -0.0000

Data Index: 411585 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 1.5619. Min Range: -1.5619

Max Act: 1.0191. Min Act: -0.0000

Data Index: 154204 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 1.5619. Min Range: -1.5619

Max Act: 1.1502. Min Act: -0.0000

Data Index: 973742 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 1.5619. Min Range: -1.5619

Max Act: 1.0371. Min Act: -0.0000

Data Index: 68384 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 1.5619. Min Range: -1.5619

Max Act: 0.9908. Min Act: -0.0000

Data Index: 590411 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 1.5619. Min Range: -1.5619

Max Act: 1.0223. Min Act: -0.0000

Data Index: 527836 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 1.5619. Min Range: -1.5619

Max Act: 1.0675. Min Act: -0.0000

Data Index: 572290 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 1.5619. Min Range: -1.5619

Max Act: 0.9938. Min Act: -0.0000

Data Index: 416516 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 1.5619. Min Range: -1.5619

Max Act: 0.9642. Min Act: -0.0000

Data Index: 40980 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 1.5619. Min Range: -1.5619

Max Act: 0.9895. Min Act: -0.0000

Data Index: 1212504 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 1.5619. Min Range: -1.5619

Max Act: 1.0018. Min Act: -0.0000

Data Index: 882288 (C4 (Web Text))

Max Activating Token Index: 441

Text #12

Max Range: 1.5619. Min Range: -1.5619

Max Act: 1.0306. Min Act: -0.0000

Data Index: 989227 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 1.5619. Min Range: -1.5619

Max Act: 0.9504. Min Act: -0.0000

Data Index: 678283 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 1.5619. Min Range: -1.5619

Max Act: 1.0177. Min Act: -0.0000

Data Index: 569373 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 1.5619. Min Range: -1.5619

Max Act: 0.9382. Min Act: -0.0000

Data Index: 785023 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 1.5619. Min Range: -1.5619

Max Act: 0.9505. Min Act: -0.0000

Data Index: 861248 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 1.5619. Min Range: -1.5619

Max Act: 0.9442. Min Act: -0.0000

Data Index: 367394 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 1.5619. Min Range: -1.5619

Max Act: 0.9392. Min Act: -0.0000

Data Index: 1085743 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 1.5619. Min Range: -1.5619

Max Act: 0.9480. Min Act: -0.0000

Data Index: 259617 (C4 (Web Text))

Max Activating Token Index: 57