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

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

Neuron 5004 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: 2.9226. Min Range: -2.9226

Max Act: 2.8236. Min Act: -0.0000

Data Index: 908759 (C4 (Web Text))

Max Activating Token Index: 952

Text #1

Max Range: 2.9226. Min Range: -2.9226

Max Act: 2.9127. Min Act: -0.0000

Data Index: 322319 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 2.9226. Min Range: -2.9226

Max Act: 2.8331. Min Act: -0.0000

Data Index: 508863 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 2.9226. Min Range: -2.9226

Max Act: 2.5617. Min Act: -0.0000

Data Index: 1373429 (Python Code)

Max Activating Token Index: 779

Text #4

Max Range: 2.9226. Min Range: -2.9226

Max Act: 2.6603. Min Act: -0.0000

Data Index: 421902 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 2.9226. Min Range: -2.9226

Max Act: 2.9065. Min Act: -0.0000

Data Index: 1067964 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 2.9226. Min Range: -2.9226

Max Act: 2.6995. Min Act: -0.0000

Data Index: 186097 (C4 (Web Text))

Max Activating Token Index: 461

Text #7

Max Range: 2.9226. Min Range: -2.9226

Max Act: 2.5564. Min Act: -0.0000

Data Index: 1578640 (Python Code)

Max Activating Token Index: 793

Text #8

Max Range: 2.9226. Min Range: -2.9226

Max Act: 2.5444. Min Act: -0.0000

Data Index: 988974 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 2.9226. Min Range: -2.9226

Max Act: 2.5102. Min Act: -0.0000

Data Index: 119276 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 2.9226. Min Range: -2.9226

Max Act: 2.6505. Min Act: -0.0000

Data Index: 596336 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 2.9226. Min Range: -2.9226

Max Act: 2.5998. Min Act: -0.0000

Data Index: 1154244 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 2.9226. Min Range: -2.9226

Max Act: 2.4770. Min Act: -0.0000

Data Index: 39159 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 2.9226. Min Range: -2.9226

Max Act: 2.5940. Min Act: -0.0000

Data Index: 1576799 (Python Code)

Max Activating Token Index: 112

Text #14

Max Range: 2.9226. Min Range: -2.9226

Max Act: 2.7509. Min Act: -0.0000

Data Index: 540284 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 2.9226. Min Range: -2.9226

Max Act: 2.7143. Min Act: -0.0000

Data Index: 1587687 (Python Code)

Max Activating Token Index: 622

Text #16

Max Range: 2.9226. Min Range: -2.9226

Max Act: 2.9226. Min Act: -0.0000

Data Index: 996785 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 2.9226. Min Range: -2.9226

Max Act: 2.5490. Min Act: -0.0000

Data Index: 1303596 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 2.9226. Min Range: -2.9226

Max Act: 2.4130. Min Act: -0.0000

Data Index: 1385379 (Python Code)

Max Activating Token Index: 919

Text #19

Max Range: 2.9226. Min Range: -2.9226

Max Act: 2.3799. Min Act: -0.0000

Data Index: 291289 (C4 (Web Text))

Max Activating Token Index: 31