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

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

Neuron 1268 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.5282. Min Act: -0.0000

Data Index: 1000340 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4372. Min Act: -0.0000

Data Index: 778545 (C4 (Web Text))

Max Activating Token Index: 635

Text #2

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4168. Min Act: -0.0000

Data Index: 323050 (C4 (Web Text))

Max Activating Token Index: 276

Text #3

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.3657. Min Act: -0.0000

Data Index: 1352905 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.3656. Min Act: -0.0000

Data Index: 895916 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.3529. Min Act: -0.0000

Data Index: 853779 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.3642. Min Act: -0.0000

Data Index: 833971 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.3780. Min Act: -0.0000

Data Index: 1353666 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.3552. Min Act: -0.0000

Data Index: 212999 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.3214. Min Act: -0.0000

Data Index: 1138133 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.3573. Min Act: -0.0000

Data Index: 1054119 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.3329. Min Act: -0.0000

Data Index: 1268691 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.3263. Min Act: -0.0000

Data Index: 449249 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.3359. Min Act: -0.0000

Data Index: 710002 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.3171. Min Act: -0.0000

Data Index: 30854 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.3371. Min Act: -0.0000

Data Index: 585446 (C4 (Web Text))

Max Activating Token Index: 619

Text #16

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.2863. Min Act: -0.0000

Data Index: 801985 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.2949. Min Act: -0.0000

Data Index: 1236131 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.3039. Min Act: -0.0000

Data Index: 1092516 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.3036. Min Act: -0.0000

Data Index: 395878 (C4 (Web Text))

Max Activating Token Index: 67