Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2548 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.6419. Min Act: -0.0001

Data Index: 1268170 (C4 (Web Text))

Max Activating Token Index: 449

Text #1

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.6146. Min Act: -0.0001

Data Index: 1231027 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.3841. Min Act: -0.0001

Data Index: 915916 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.6407. Min Act: -0.0001

Data Index: 772609 (C4 (Web Text))

Max Activating Token Index: 587

Text #4

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.2363. Min Act: -0.0001

Data Index: 545600 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.3771. Min Act: -0.0001

Data Index: 546915 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.2216. Min Act: -0.0001

Data Index: 1257903 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.6628. Min Act: -0.0001

Data Index: 1224259 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.1553. Min Act: -0.0001

Data Index: 175118 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.2251. Min Act: -0.0001

Data Index: 67275 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.2043. Min Act: -0.0001

Data Index: 339677 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.0233. Min Act: -0.0001

Data Index: 1094638 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.1577. Min Act: -0.0001

Data Index: 1090739 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.0965. Min Act: -0.0001

Data Index: 323103 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.2252. Min Act: -0.0001

Data Index: 1080887 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 3.6628. Min Range: -3.6628

Max Act: 2.6718. Min Act: -0.0001

Data Index: 566201 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.2033. Min Act: -0.0001

Data Index: 1051207 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.0880. Min Act: -0.0001

Data Index: 1061507 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.1814. Min Act: -0.0001

Data Index: 1189550 (C4 (Web Text))

Max Activating Token Index: 842

Text #19

Max Range: 3.6628. Min Range: -3.6628

Max Act: 2.8808. Min Act: -0.0001

Data Index: 660153 (C4 (Web Text))

Max Activating Token Index: 976