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

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

Neuron 3280 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0988. Min Range: -1.0988

Max Act: 1.0988. Min Act: -0.0000

Data Index: 708635 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 1.0988. Min Range: -1.0988

Max Act: 1.0577. Min Act: 0.0000

Data Index: 224917 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 1.0988. Min Range: -1.0988

Max Act: 0.9860. Min Act: -0.0000

Data Index: 48929 (C4 (Web Text))

Max Activating Token Index: 897

Text #3

Max Range: 1.0988. Min Range: -1.0988

Max Act: 0.9285. Min Act: -0.0000

Data Index: 681484 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 1.0988. Min Range: -1.0988

Max Act: 0.9202. Min Act: -0.0000

Data Index: 904236 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 1.0988. Min Range: -1.0988

Max Act: 0.8587. Min Act: -0.0000

Data Index: 281279 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 1.0988. Min Range: -1.0988

Max Act: 0.8879. Min Act: -0.0000

Data Index: 96770 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 1.0988. Min Range: -1.0988

Max Act: 0.8483. Min Act: 0.0000

Data Index: 985843 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 1.0988. Min Range: -1.0988

Max Act: 0.8120. Min Act: -0.0000

Data Index: 749729 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 1.0988. Min Range: -1.0988

Max Act: 0.7886. Min Act: -0.0000

Data Index: 703333 (C4 (Web Text))

Max Activating Token Index: 791

Text #10

Max Range: 1.0988. Min Range: -1.0988

Max Act: 0.7861. Min Act: -0.0000

Data Index: 772389 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 1.0988. Min Range: -1.0988

Max Act: 0.7838. Min Act: -0.0000

Data Index: 902160 (C4 (Web Text))

Max Activating Token Index: 266

Text #12

Max Range: 1.0988. Min Range: -1.0988

Max Act: 0.7460. Min Act: -0.0000

Data Index: 1281225 (C4 (Web Text))

Max Activating Token Index: 773

Text #13

Max Range: 1.0988. Min Range: -1.0988

Max Act: 0.7439. Min Act: -0.0000

Data Index: 1211099 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 1.0988. Min Range: -1.0988

Max Act: 0.7142. Min Act: -0.0000

Data Index: 449075 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 1.0988. Min Range: -1.0988

Max Act: 0.7569. Min Act: -0.0000

Data Index: 323207 (C4 (Web Text))

Max Activating Token Index: 573

Text #16

Max Range: 1.0988. Min Range: -1.0988

Max Act: 0.7231. Min Act: -0.0001

Data Index: 1009180 (C4 (Web Text))

Max Activating Token Index: 892

Text #17

Max Range: 1.0988. Min Range: -1.0988

Max Act: 0.7246. Min Act: -0.0000

Data Index: 228152 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 1.0988. Min Range: -1.0988

Max Act: 0.7425. Min Act: 0.0000

Data Index: 979858 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 1.0988. Min Range: -1.0988

Max Act: 0.7231. Min Act: -0.0000

Data Index: 335195 (C4 (Web Text))

Max Activating Token Index: 680