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

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

Neuron 882 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.8773. Min Act: -0.0001

Data Index: 1033203 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.8252. Min Act: -0.0001

Data Index: 939613 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.8054. Min Act: -0.0001

Data Index: 1173874 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.7966. Min Act: -0.0001

Data Index: 333058 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.7253. Min Act: -0.0001

Data Index: 972276 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.8155. Min Act: -0.0001

Data Index: 1234522 (C4 (Web Text))

Max Activating Token Index: 393

Text #6

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.7371. Min Act: -0.0001

Data Index: 751630 (C4 (Web Text))

Max Activating Token Index: 690

Text #7

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.7445. Min Act: -0.0001

Data Index: 1167236 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.7462. Min Act: -0.0001

Data Index: 1115456 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.7590. Min Act: -0.0001

Data Index: 111378 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.7587. Min Act: -0.0001

Data Index: 604789 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.7969. Min Act: -0.0001

Data Index: 1181969 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.7435. Min Act: -0.0001

Data Index: 1148657 (C4 (Web Text))

Max Activating Token Index: 519

Text #13

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.7076. Min Act: -0.0001

Data Index: 817907 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.7406. Min Act: -0.0001

Data Index: 816347 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6790. Min Act: -0.0001

Data Index: 622888 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.7130. Min Act: -0.0001

Data Index: 591226 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.7372. Min Act: -0.0001

Data Index: 1138839 (C4 (Web Text))

Max Activating Token Index: 510

Text #18

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.7262. Min Act: -0.0001

Data Index: 54503 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.7233. Min Act: -0.0001

Data Index: 952599 (C4 (Web Text))

Max Activating Token Index: 761