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

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

Neuron 748 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2999. Min Range: -1.2999

Max Act: 1.2999. Min Act: -0.0000

Data Index: 1217544 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 1.2999. Min Range: -1.2999

Max Act: 1.1320. Min Act: -0.0000

Data Index: 86145 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 1.2999. Min Range: -1.2999

Max Act: 1.2259. Min Act: -0.0000

Data Index: 251780 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 1.2999. Min Range: -1.2999

Max Act: 1.0565. Min Act: -0.0000

Data Index: 420407 (C4 (Web Text))

Max Activating Token Index: 449

Text #4

Max Range: 1.2999. Min Range: -1.2999

Max Act: 1.0459. Min Act: -0.0000

Data Index: 411906 (C4 (Web Text))

Max Activating Token Index: 814

Text #5

Max Range: 1.2999. Min Range: -1.2999

Max Act: 0.9291. Min Act: -0.0000

Data Index: 857259 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 1.2999. Min Range: -1.2999

Max Act: 0.9630. Min Act: -0.0000

Data Index: 1186973 (C4 (Web Text))

Max Activating Token Index: 883

Text #7

Max Range: 1.2999. Min Range: -1.2999

Max Act: 0.8974. Min Act: -0.0000

Data Index: 416009 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 1.2999. Min Range: -1.2999

Max Act: 0.9261. Min Act: -0.0000

Data Index: 44760 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 1.2999. Min Range: -1.2999

Max Act: 0.8823. Min Act: -0.0000

Data Index: 240648 (C4 (Web Text))

Max Activating Token Index: 765

Text #10

Max Range: 1.2999. Min Range: -1.2999

Max Act: 0.8579. Min Act: -0.0000

Data Index: 34517 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 1.2999. Min Range: -1.2999

Max Act: 0.8017. Min Act: -0.0000

Data Index: 249784 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 1.2999. Min Range: -1.2999

Max Act: 0.8132. Min Act: -0.0000

Data Index: 356312 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 1.2999. Min Range: -1.2999

Max Act: 0.8071. Min Act: -0.0000

Data Index: 816951 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 1.2999. Min Range: -1.2999

Max Act: 0.7569. Min Act: -0.0000

Data Index: 1016759 (C4 (Web Text))

Max Activating Token Index: 279

Text #15

Max Range: 1.2999. Min Range: -1.2999

Max Act: 0.8014. Min Act: -0.0000

Data Index: 551740 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 1.2999. Min Range: -1.2999

Max Act: 0.8316. Min Act: -0.0000

Data Index: 899622 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 1.2999. Min Range: -1.2999

Max Act: 0.7949. Min Act: -0.0000

Data Index: 798165 (C4 (Web Text))

Max Activating Token Index: 181

Text #18

Max Range: 1.2999. Min Range: -1.2999

Max Act: 0.8026. Min Act: -0.0000

Data Index: 795437 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 1.2999. Min Range: -1.2999

Max Act: 0.7731. Min Act: -0.0000

Data Index: 681265 (C4 (Web Text))

Max Activating Token Index: 576