Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1515 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0765. Min Range: -1.0765

Max Act: 1.0765. Min Act: -0.0001

Data Index: 1330729 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.9864. Min Act: -0.0001

Data Index: 214464 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.8203. Min Act: -0.0001

Data Index: 928902 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.8194. Min Act: -0.0001

Data Index: 724598 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.6927. Min Act: -0.0001

Data Index: 23559 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.7408. Min Act: -0.0001

Data Index: 182271 (C4 (Web Text))

Max Activating Token Index: 979

Text #6

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.7697. Min Act: -0.0001

Data Index: 286905 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.7466. Min Act: -0.0001

Data Index: 1003512 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.6943. Min Act: -0.0001

Data Index: 948165 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.7077. Min Act: -0.0001

Data Index: 949188 (C4 (Web Text))

Max Activating Token Index: 914

Text #10

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.7152. Min Act: -0.0001

Data Index: 786474 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.6894. Min Act: -0.0001

Data Index: 228727 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.7386. Min Act: -0.0001

Data Index: 1246734 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.6630. Min Act: -0.0001

Data Index: 149013 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.6290. Min Act: -0.0001

Data Index: 857151 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.6724. Min Act: -0.0001

Data Index: 804361 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.6507. Min Act: -0.0001

Data Index: 1095475 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.6617. Min Act: -0.0001

Data Index: 1073320 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.6642. Min Act: -0.0001

Data Index: 813923 (C4 (Web Text))

Max Activating Token Index: 877

Text #19

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.6335. Min Act: -0.0001

Data Index: 260767 (C4 (Web Text))

Max Activating Token Index: 210