Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1040 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.8750. Min Act: -0.0000

Data Index: 641306 (The Pile)

Max Activating Token Index: 941

Text #1

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.7715. Min Act: -0.0000

Data Index: 290704 (The Pile)

Max Activating Token Index: 946

Text #2

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.7643. Min Act: -0.0000

Data Index: 1349169 (The Pile)

Max Activating Token Index: 790

Text #3

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.7246. Min Act: -0.0000

Data Index: 1104298 (The Pile)

Max Activating Token Index: 5

Text #4

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.7185. Min Act: -0.0000

Data Index: 1847931 (The Pile)

Max Activating Token Index: 401

Text #5

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.6876. Min Act: -0.0000

Data Index: 1763464 (The Pile)

Max Activating Token Index: 860

Text #6

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.7128. Min Act: -0.0000

Data Index: 1318234 (The Pile)

Max Activating Token Index: 134

Text #7

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.7078. Min Act: -0.0000

Data Index: 839663 (The Pile)

Max Activating Token Index: 173

Text #8

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.7037. Min Act: -0.0000

Data Index: 1606907 (The Pile)

Max Activating Token Index: 417

Text #9

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.7312. Min Act: -0.0000

Data Index: 892730 (The Pile)

Max Activating Token Index: 185

Text #10

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.7162. Min Act: -0.0000

Data Index: 79179 (The Pile)

Max Activating Token Index: 1000

Text #11

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.6386. Min Act: -0.0000

Data Index: 771803 (The Pile)

Max Activating Token Index: 812

Text #12

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.6968. Min Act: -0.0000

Data Index: 1350383 (The Pile)

Max Activating Token Index: 365

Text #13

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.6787. Min Act: -0.0000

Data Index: 1661497 (The Pile)

Max Activating Token Index: 326

Text #14

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.6724. Min Act: -0.0000

Data Index: 606770 (The Pile)

Max Activating Token Index: 952

Text #15

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.6782. Min Act: -0.0000

Data Index: 483718 (The Pile)

Max Activating Token Index: 543

Text #16

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.7234. Min Act: -0.0000

Data Index: 1469674 (The Pile)

Max Activating Token Index: 125

Text #17

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.6937. Min Act: -0.0000

Data Index: 619276 (The Pile)

Max Activating Token Index: 566

Text #18

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.6823. Min Act: -0.0000

Data Index: 1282883 (The Pile)

Max Activating Token Index: 741

Text #19

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.6874. Min Act: -0.0000

Data Index: 181238 (The Pile)

Max Activating Token Index: 1011