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

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

Neuron 1965 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.7009. Min Act: -0.0001

Data Index: 349723 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.7582. Min Act: -0.0001

Data Index: 458854 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.6284. Min Act: -0.0001

Data Index: 807362 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.6718. Min Act: -0.0001

Data Index: 773553 (C4 (Web Text))

Max Activating Token Index: 735

Text #4

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.6447. Min Act: -0.0001

Data Index: 1075632 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.6257. Min Act: -0.0001

Data Index: 331595 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.6135. Min Act: -0.0001

Data Index: 1032529 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.6380. Min Act: -0.0002

Data Index: 882011 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.6397. Min Act: -0.0001

Data Index: 613541 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.6401. Min Act: -0.0002

Data Index: 881948 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.6619. Min Act: -0.0001

Data Index: 1125530 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.5865. Min Act: -0.0001

Data Index: 1036143 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.5496. Min Act: -0.0001

Data Index: 370077 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.5863. Min Act: -0.0001

Data Index: 1264217 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.5660. Min Act: -0.0001

Data Index: 779959 (C4 (Web Text))

Max Activating Token Index: 999

Text #15

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.5832. Min Act: -0.0001

Data Index: 861393 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.5642. Min Act: -0.0001

Data Index: 116568 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.6006. Min Act: -0.0001

Data Index: 329116 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.5954. Min Act: -0.0001

Data Index: 1129826 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.5716. Min Act: -0.0001

Data Index: 41613 (C4 (Web Text))

Max Activating Token Index: 900