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

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

Neuron 2657 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.9692. Min Act: -0.0001

Data Index: 347597 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 1.0086. Min Range: -1.0086

Max Act: 1.0086. Min Act: -0.0001

Data Index: 204227 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.9073. Min Act: -0.0001

Data Index: 393804 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.9106. Min Act: -0.0001

Data Index: 2099 (C4 (Web Text))

Max Activating Token Index: 776

Text #4

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.9533. Min Act: -0.0001

Data Index: 573083 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.9326. Min Act: -0.0001

Data Index: 180568 (C4 (Web Text))

Max Activating Token Index: 616

Text #6

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.9198. Min Act: -0.0001

Data Index: 595695 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.8372. Min Act: -0.0001

Data Index: 250495 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.8685. Min Act: -0.0001

Data Index: 687018 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.8588. Min Act: -0.0001

Data Index: 44059 (C4 (Web Text))

Max Activating Token Index: 1005

Text #10

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.8907. Min Act: -0.0001

Data Index: 1184385 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.8652. Min Act: -0.0001

Data Index: 1068967 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.8865. Min Act: -0.0001

Data Index: 1166546 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.8286. Min Act: -0.0001

Data Index: 656893 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.8754. Min Act: -0.0001

Data Index: 359363 (C4 (Web Text))

Max Activating Token Index: 99

Text #15

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.9002. Min Act: -0.0001

Data Index: 598258 (C4 (Web Text))

Max Activating Token Index: 658

Text #16

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.8152. Min Act: -0.0001

Data Index: 548423 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.8792. Min Act: -0.0001

Data Index: 100101 (C4 (Web Text))

Max Activating Token Index: 761

Text #18

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.8820. Min Act: -0.0001

Data Index: 666794 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.8251. Min Act: -0.0001

Data Index: 1248577 (C4 (Web Text))

Max Activating Token Index: 456