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

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

Neuron 71 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: 0.8743. Min Range: -0.8743

Max Act: 0.8743. Min Act: 0.0000

Data Index: 930672 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.6246. Min Act: 0.0000

Data Index: 1215674 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.6020. Min Act: -0.0000

Data Index: 1268623 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.6088. Min Act: -0.0000

Data Index: 228298 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.6139. Min Act: 0.0001

Data Index: 1168932 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.6099. Min Act: 0.0001

Data Index: 639555 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.5808. Min Act: 0.0002

Data Index: 1230723 (C4 (Web Text))

Max Activating Token Index: 513

Text #7

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.5782. Min Act: 0.0000

Data Index: 812538 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.5948. Min Act: 0.0002

Data Index: 364591 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.5369. Min Act: 0.0002

Data Index: 943310 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.5206. Min Act: 0.0001

Data Index: 813726 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.5353. Min Act: -0.0000

Data Index: 987331 (C4 (Web Text))

Max Activating Token Index: 545

Text #12

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.5481. Min Act: -0.0000

Data Index: 713795 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.5515. Min Act: -0.0000

Data Index: 659310 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.5182. Min Act: 0.0001

Data Index: 42233 (C4 (Web Text))

Max Activating Token Index: 765

Text #15

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.4755. Min Act: -0.0000

Data Index: 531354 (C4 (Web Text))

Max Activating Token Index: 264

Text #16

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.4873. Min Act: 0.0000

Data Index: 1247313 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.4835. Min Act: 0.0002

Data Index: 333970 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.4757. Min Act: 0.0002

Data Index: 292702 (C4 (Web Text))

Max Activating Token Index: 295

Text #19

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.4727. Min Act: 0.0001

Data Index: 224037 (C4 (Web Text))

Max Activating Token Index: 390