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

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

Neuron 1086 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0286. Min Range: -1.0286

Max Act: 1.0286. Min Act: -0.0000

Data Index: 875590 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 1.0286. Min Range: -1.0286

Max Act: 0.9851. Min Act: -0.0000

Data Index: 179527 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 1.0286. Min Range: -1.0286

Max Act: 1.0055. Min Act: -0.0000

Data Index: 25157 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 1.0286. Min Range: -1.0286

Max Act: 1.0192. Min Act: -0.0001

Data Index: 500965 (C4 (Web Text))

Max Activating Token Index: 809

Text #4

Max Range: 1.0286. Min Range: -1.0286

Max Act: 0.9703. Min Act: -0.0001

Data Index: 993084 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 1.0286. Min Range: -1.0286

Max Act: 0.9406. Min Act: -0.0001

Data Index: 516382 (C4 (Web Text))

Max Activating Token Index: 678

Text #6

Max Range: 1.0286. Min Range: -1.0286

Max Act: 0.9373. Min Act: -0.0001

Data Index: 818846 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 1.0286. Min Range: -1.0286

Max Act: 0.9063. Min Act: -0.0001

Data Index: 17652 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 1.0286. Min Range: -1.0286

Max Act: 0.9375. Min Act: -0.0001

Data Index: 799613 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 1.0286. Min Range: -1.0286

Max Act: 0.9008. Min Act: -0.0001

Data Index: 532320 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 1.0286. Min Range: -1.0286

Max Act: 0.8948. Min Act: -0.0000

Data Index: 516393 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 1.0286. Min Range: -1.0286

Max Act: 0.8821. Min Act: -0.0001

Data Index: 133897 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 1.0286. Min Range: -1.0286

Max Act: 0.9122. Min Act: -0.0001

Data Index: 968989 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 1.0286. Min Range: -1.0286

Max Act: 0.8513. Min Act: -0.0000

Data Index: 864138 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 1.0286. Min Range: -1.0286

Max Act: 0.8439. Min Act: -0.0001

Data Index: 35168 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 1.0286. Min Range: -1.0286

Max Act: 0.8664. Min Act: -0.0001

Data Index: 798460 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 1.0286. Min Range: -1.0286

Max Act: 0.7867. Min Act: -0.0000

Data Index: 597481 (C4 (Web Text))

Max Activating Token Index: 574

Text #17

Max Range: 1.0286. Min Range: -1.0286

Max Act: 0.8122. Min Act: -0.0001

Data Index: 33630 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 1.0286. Min Range: -1.0286

Max Act: 0.8525. Min Act: -0.0000

Data Index: 289850 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 1.0286. Min Range: -1.0286

Max Act: 0.8315. Min Act: -0.0001

Data Index: 635981 (C4 (Web Text))

Max Activating Token Index: 620