Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5316 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.6982. Min Act: -0.0000

Data Index: 74012 (C4 (Web Text))

Max Activating Token Index: 607

Text #1

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.6994. Min Act: -0.0000

Data Index: 146089 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5456. Min Act: -0.0000

Data Index: 625884 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5439. Min Act: -0.0000

Data Index: 689873 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5171. Min Act: -0.0000

Data Index: 633581 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5016. Min Act: -0.0000

Data Index: 1035176 (C4 (Web Text))

Max Activating Token Index: 458

Text #6

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5040. Min Act: -0.0000

Data Index: 1212226 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4754. Min Act: 0.0000

Data Index: 612349 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4522. Min Act: -0.0000

Data Index: 1214982 (C4 (Web Text))

Max Activating Token Index: 682

Text #9

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4965. Min Act: -0.0000

Data Index: 475566 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4879. Min Act: -0.0000

Data Index: 939749 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4682. Min Act: -0.0000

Data Index: 616423 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4357. Min Act: -0.0000

Data Index: 576162 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4517. Min Act: 0.0000

Data Index: 1198775 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4353. Min Act: -0.0000

Data Index: 523395 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4727. Min Act: -0.0000

Data Index: 490362 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4127. Min Act: -0.0000

Data Index: 1324532 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4557. Min Act: -0.0000

Data Index: 400908 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4325. Min Act: -0.0000

Data Index: 84927 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4095. Min Act: -0.0000

Data Index: 1164207 (C4 (Web Text))

Max Activating Token Index: 674