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

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

Neuron 3009 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8998. Min Range: -1.8998

Max Act: 1.8998. Min Act: -0.0001

Data Index: 1436658 (Python Code)

Max Activating Token Index: 79

Text #1

Max Range: 1.8998. Min Range: -1.8998

Max Act: 1.7722. Min Act: -0.0001

Data Index: 1206554 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 1.8998. Min Range: -1.8998

Max Act: 1.7720. Min Act: -0.0001

Data Index: 335526 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 1.8998. Min Range: -1.8998

Max Act: 1.7212. Min Act: -0.0001

Data Index: 1601153 (Python Code)

Max Activating Token Index: 568

Text #4

Max Range: 1.8998. Min Range: -1.8998

Max Act: 1.7705. Min Act: -0.0001

Data Index: 66964 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 1.8998. Min Range: -1.8998

Max Act: 1.6420. Min Act: -0.0001

Data Index: 854291 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 1.8998. Min Range: -1.8998

Max Act: 1.6596. Min Act: -0.0001

Data Index: 605386 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 1.8998. Min Range: -1.8998

Max Act: 1.5638. Min Act: -0.0001

Data Index: 832118 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 1.8998. Min Range: -1.8998

Max Act: 1.6197. Min Act: -0.0001

Data Index: 520206 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 1.8998. Min Range: -1.8998

Max Act: 1.6012. Min Act: -0.0001

Data Index: 1004061 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 1.8998. Min Range: -1.8998

Max Act: 1.5079. Min Act: -0.0001

Data Index: 1062750 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 1.8998. Min Range: -1.8998

Max Act: 1.5828. Min Act: -0.0001

Data Index: 1640566 (Python Code)

Max Activating Token Index: 24

Text #12

Max Range: 1.8998. Min Range: -1.8998

Max Act: 1.4800. Min Act: -0.0001

Data Index: 1568153 (Python Code)

Max Activating Token Index: 715

Text #13

Max Range: 1.8998. Min Range: -1.8998

Max Act: 1.6558. Min Act: -0.0001

Data Index: 70012 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 1.8998. Min Range: -1.8998

Max Act: 1.5556. Min Act: -0.0001

Data Index: 654837 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 1.8998. Min Range: -1.8998

Max Act: 1.6454. Min Act: -0.0001

Data Index: 568412 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 1.8998. Min Range: -1.8998

Max Act: 1.5496. Min Act: -0.0001

Data Index: 619116 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 1.8998. Min Range: -1.8998

Max Act: 1.5345. Min Act: -0.0001

Data Index: 1514220 (Python Code)

Max Activating Token Index: 226

Text #18

Max Range: 1.8998. Min Range: -1.8998

Max Act: 1.5301. Min Act: -0.0001

Data Index: 785977 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 1.8998. Min Range: -1.8998

Max Act: 1.4390. Min Act: -0.0001

Data Index: 1050646 (C4 (Web Text))

Max Activating Token Index: 935