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

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

Neuron 2098 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: 1.6721. Min Range: -1.6721

Max Act: 1.6721. Min Act: -0.0000

Data Index: 500743 (C4 (Web Text))

Max Activating Token Index: 388

Text #1

Max Range: 1.6721. Min Range: -1.6721

Max Act: 1.5663. Min Act: -0.0000

Data Index: 1002963 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 1.6721. Min Range: -1.6721

Max Act: 1.6410. Min Act: -0.0000

Data Index: 16090 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 1.6721. Min Range: -1.6721

Max Act: 1.6121. Min Act: -0.0000

Data Index: 62021 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 1.6721. Min Range: -1.6721

Max Act: 1.5823. Min Act: -0.0000

Data Index: 1080191 (C4 (Web Text))

Max Activating Token Index: 472

Text #5

Max Range: 1.6721. Min Range: -1.6721

Max Act: 1.5763. Min Act: -0.0001

Data Index: 1149100 (C4 (Web Text))

Max Activating Token Index: 501

Text #6

Max Range: 1.6721. Min Range: -1.6721

Max Act: 1.4723. Min Act: -0.0000

Data Index: 1335535 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 1.6721. Min Range: -1.6721

Max Act: 1.5318. Min Act: -0.0000

Data Index: 902200 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 1.6721. Min Range: -1.6721

Max Act: 1.5264. Min Act: -0.0001

Data Index: 551559 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 1.6721. Min Range: -1.6721

Max Act: 1.6146. Min Act: -0.0000

Data Index: 853101 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 1.6721. Min Range: -1.6721

Max Act: 1.6118. Min Act: -0.0000

Data Index: 579372 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 1.6721. Min Range: -1.6721

Max Act: 1.5128. Min Act: -0.0001

Data Index: 472237 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 1.6721. Min Range: -1.6721

Max Act: 1.4161. Min Act: -0.0000

Data Index: 1234667 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 1.6721. Min Range: -1.6721

Max Act: 1.4934. Min Act: -0.0000

Data Index: 1295356 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 1.6721. Min Range: -1.6721

Max Act: 1.4777. Min Act: -0.0000

Data Index: 1262865 (C4 (Web Text))

Max Activating Token Index: 481

Text #15

Max Range: 1.6721. Min Range: -1.6721

Max Act: 1.4409. Min Act: -0.0000

Data Index: 590686 (C4 (Web Text))

Max Activating Token Index: 316

Text #16

Max Range: 1.6721. Min Range: -1.6721

Max Act: 1.4364. Min Act: -0.0000

Data Index: 281782 (C4 (Web Text))

Max Activating Token Index: 587

Text #17

Max Range: 1.6721. Min Range: -1.6721

Max Act: 1.4234. Min Act: -0.0000

Data Index: 459154 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 1.6721. Min Range: -1.6721

Max Act: 1.3103. Min Act: -0.0000

Data Index: 782139 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 1.6721. Min Range: -1.6721

Max Act: 1.2766. Min Act: -0.0001

Data Index: 155066 (C4 (Web Text))

Max Activating Token Index: 627