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

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

Neuron 3891 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9018. Min Range: -0.9018

Max Act: 0.9018. Min Act: -0.0000

Data Index: 958450 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 0.9018. Min Range: -0.9018

Max Act: 0.7973. Min Act: -0.0000

Data Index: 1153266 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 0.9018. Min Range: -0.9018

Max Act: 0.8514. Min Act: -0.0000

Data Index: 271370 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 0.9018. Min Range: -0.9018

Max Act: 0.7728. Min Act: -0.0000

Data Index: 143389 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 0.9018. Min Range: -0.9018

Max Act: 0.6887. Min Act: -0.0000

Data Index: 459714 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 0.9018. Min Range: -0.9018

Max Act: 0.7992. Min Act: -0.0000

Data Index: 1038410 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 0.9018. Min Range: -0.9018

Max Act: 0.8197. Min Act: -0.0000

Data Index: 73719 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 0.9018. Min Range: -0.9018

Max Act: 0.7462. Min Act: -0.0000

Data Index: 869784 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 0.9018. Min Range: -0.9018

Max Act: 0.7116. Min Act: -0.0000

Data Index: 415563 (C4 (Web Text))

Max Activating Token Index: 330

Text #9

Max Range: 0.9018. Min Range: -0.9018

Max Act: 0.6092. Min Act: -0.0000

Data Index: 51998 (C4 (Web Text))

Max Activating Token Index: 569

Text #10

Max Range: 0.9018. Min Range: -0.9018

Max Act: 0.6412. Min Act: -0.0000

Data Index: 687417 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 0.9018. Min Range: -0.9018

Max Act: 0.6835. Min Act: -0.0000

Data Index: 592378 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 0.9018. Min Range: -0.9018

Max Act: 0.5813. Min Act: -0.0000

Data Index: 334152 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 0.9018. Min Range: -0.9018

Max Act: 0.6424. Min Act: -0.0000

Data Index: 919413 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 0.9018. Min Range: -0.9018

Max Act: 0.5991. Min Act: -0.0000

Data Index: 748063 (C4 (Web Text))

Max Activating Token Index: 474

Text #15

Max Range: 0.9018. Min Range: -0.9018

Max Act: 0.5628. Min Act: -0.0000

Data Index: 38272 (C4 (Web Text))

Max Activating Token Index: 234

Text #16

Max Range: 0.9018. Min Range: -0.9018

Max Act: 0.5874. Min Act: -0.0000

Data Index: 1283494 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 0.9018. Min Range: -0.9018

Max Act: 0.5612. Min Act: -0.0000

Data Index: 1296933 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 0.9018. Min Range: -0.9018

Max Act: 0.5902. Min Act: -0.0000

Data Index: 299659 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 0.9018. Min Range: -0.9018

Max Act: 0.6117. Min Act: -0.0000

Data Index: 1211955 (C4 (Web Text))

Max Activating Token Index: 890