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

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

Neuron 3681 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.8210. Min Act: -0.0000

Data Index: 192051 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.7295. Min Act: -0.0000

Data Index: 721706 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.7425. Min Act: -0.0000

Data Index: 807059 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.6305. Min Act: -0.0000

Data Index: 507001 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.6136. Min Act: -0.0000

Data Index: 809248 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.6220. Min Act: -0.0000

Data Index: 234240 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.6150. Min Act: -0.0000

Data Index: 435820 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5573. Min Act: -0.0000

Data Index: 433160 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5307. Min Act: -0.0000

Data Index: 579827 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5582. Min Act: -0.0000

Data Index: 968074 (C4 (Web Text))

Max Activating Token Index: 671

Text #10

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5645. Min Act: -0.0000

Data Index: 668826 (C4 (Web Text))

Max Activating Token Index: 693

Text #11

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5357. Min Act: -0.0000

Data Index: 455343 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5418. Min Act: -0.0000

Data Index: 649279 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5711. Min Act: -0.0000

Data Index: 369792 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.4848. Min Act: -0.0000

Data Index: 1020620 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5192. Min Act: -0.0000

Data Index: 23919 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.4556. Min Act: -0.0000

Data Index: 380099 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5029. Min Act: 0.0000

Data Index: 1283362 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.4792. Min Act: -0.0000

Data Index: 1609614 (Python Code)

Max Activating Token Index: 197

Text #19

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.4479. Min Act: -0.0000

Data Index: 677288 (C4 (Web Text))

Max Activating Token Index: 482