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

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

Neuron 1767 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: 2.7050. Min Range: -2.7050

Max Act: 2.7050. Min Act: -0.0000

Data Index: 1352473 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 2.7050. Min Range: -2.7050

Max Act: 2.5888. Min Act: -0.0000

Data Index: 1226344 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 2.7050. Min Range: -2.7050

Max Act: 2.4291. Min Act: -0.0000

Data Index: 171968 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 2.7050. Min Range: -2.7050

Max Act: 2.3783. Min Act: -0.0000

Data Index: 1002926 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 2.7050. Min Range: -2.7050

Max Act: 2.3258. Min Act: -0.0000

Data Index: 775324 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 2.7050. Min Range: -2.7050

Max Act: 2.1105. Min Act: -0.0000

Data Index: 783002 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 2.7050. Min Range: -2.7050

Max Act: 2.2138. Min Act: -0.0000

Data Index: 366654 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 2.7050. Min Range: -2.7050

Max Act: 1.9516. Min Act: -0.0000

Data Index: 787730 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 2.7050. Min Range: -2.7050

Max Act: 2.0594. Min Act: -0.0000

Data Index: 1278980 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 2.7050. Min Range: -2.7050

Max Act: 2.0622. Min Act: -0.0000

Data Index: 1035629 (C4 (Web Text))

Max Activating Token Index: 374

Text #10

Max Range: 2.7050. Min Range: -2.7050

Max Act: 2.0381. Min Act: -0.0000

Data Index: 743221 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 2.7050. Min Range: -2.7050

Max Act: 2.0472. Min Act: -0.0000

Data Index: 661698 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 2.7050. Min Range: -2.7050

Max Act: 2.1294. Min Act: -0.0000

Data Index: 1336096 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 2.7050. Min Range: -2.7050

Max Act: 1.6721. Min Act: -0.0000

Data Index: 653521 (C4 (Web Text))

Max Activating Token Index: 1016

Text #14

Max Range: 2.7050. Min Range: -2.7050

Max Act: 1.8730. Min Act: -0.0000

Data Index: 555139 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 2.7050. Min Range: -2.7050

Max Act: 2.0923. Min Act: -0.0000

Data Index: 1207019 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 2.7050. Min Range: -2.7050

Max Act: 1.8609. Min Act: -0.0000

Data Index: 398634 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 2.7050. Min Range: -2.7050

Max Act: 2.0383. Min Act: -0.0000

Data Index: 507042 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 2.7050. Min Range: -2.7050

Max Act: 1.9243. Min Act: -0.0000

Data Index: 1158462 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 2.7050. Min Range: -2.7050

Max Act: 1.8026. Min Act: -0.0000

Data Index: 114809 (C4 (Web Text))

Max Activating Token Index: 148