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

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

Neuron 3608 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9276. Min Range: -1.9276

Max Act: 1.7856. Min Act: -0.0001

Data Index: 745539 (C4 (Web Text))

Max Activating Token Index: 499

Text #1

Max Range: 1.9276. Min Range: -1.9276

Max Act: 1.9145. Min Act: -0.0000

Data Index: 824225 (C4 (Web Text))

Max Activating Token Index: 591

Text #2

Max Range: 1.9276. Min Range: -1.9276

Max Act: 1.9276. Min Act: -0.0001

Data Index: 1212724 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 1.9276. Min Range: -1.9276

Max Act: 1.7016. Min Act: -0.0000

Data Index: 463553 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 1.9276. Min Range: -1.9276

Max Act: 1.6576. Min Act: -0.0000

Data Index: 1078117 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 1.9276. Min Range: -1.9276

Max Act: 1.6333. Min Act: -0.0001

Data Index: 485117 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 1.9276. Min Range: -1.9276

Max Act: 1.3437. Min Act: -0.0001

Data Index: 1094253 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 1.9276. Min Range: -1.9276

Max Act: 1.4613. Min Act: -0.0001

Data Index: 610865 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 1.9276. Min Range: -1.9276

Max Act: 1.4279. Min Act: -0.0001

Data Index: 832304 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 1.9276. Min Range: -1.9276

Max Act: 1.3753. Min Act: -0.0000

Data Index: 564951 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 1.9276. Min Range: -1.9276

Max Act: 1.4202. Min Act: -0.0001

Data Index: 1147084 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 1.9276. Min Range: -1.9276

Max Act: 1.3466. Min Act: -0.0001

Data Index: 846664 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 1.9276. Min Range: -1.9276

Max Act: 1.3304. Min Act: -0.0000

Data Index: 719583 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 1.9276. Min Range: -1.9276

Max Act: 1.4248. Min Act: -0.0001

Data Index: 795534 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 1.9276. Min Range: -1.9276

Max Act: 1.3249. Min Act: -0.0000

Data Index: 326222 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 1.9276. Min Range: -1.9276

Max Act: 1.0497. Min Act: -0.0001

Data Index: 433855 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 1.9276. Min Range: -1.9276

Max Act: 1.2415. Min Act: -0.0001

Data Index: 451407 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 1.9276. Min Range: -1.9276

Max Act: 1.4767. Min Act: -0.0001

Data Index: 804570 (C4 (Web Text))

Max Activating Token Index: 983

Text #18

Max Range: 1.9276. Min Range: -1.9276

Max Act: 1.2975. Min Act: -0.0000

Data Index: 719324 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 1.9276. Min Range: -1.9276

Max Act: 1.1095. Min Act: -0.0001

Data Index: 1337458 (C4 (Web Text))

Max Activating Token Index: 762