Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1770 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0239. Min Range: -1.0239

Max Act: 1.0209. Min Act: -0.0001

Data Index: 869730 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 1.0239. Min Range: -1.0239

Max Act: 1.0239. Min Act: -0.0001

Data Index: 738972 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 1.0239. Min Range: -1.0239

Max Act: 1.0011. Min Act: -0.0001

Data Index: 1277949 (C4 (Web Text))

Max Activating Token Index: 229

Text #3

Max Range: 1.0239. Min Range: -1.0239

Max Act: 1.0055. Min Act: -0.0001

Data Index: 878662 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 1.0239. Min Range: -1.0239

Max Act: 1.0130. Min Act: -0.0001

Data Index: 720084 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.9973. Min Act: -0.0000

Data Index: 348511 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.8457. Min Act: -0.0001

Data Index: 753335 (C4 (Web Text))

Max Activating Token Index: 426

Text #7

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.8972. Min Act: -0.0001

Data Index: 898722 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.8730. Min Act: -0.0000

Data Index: 72502 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.8627. Min Act: -0.0001

Data Index: 948578 (C4 (Web Text))

Max Activating Token Index: 703

Text #10

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.8552. Min Act: -0.0000

Data Index: 1296632 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.8549. Min Act: -0.0000

Data Index: 1335750 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.9013. Min Act: -0.0001

Data Index: 1316213 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.8650. Min Act: -0.0001

Data Index: 1279638 (C4 (Web Text))

Max Activating Token Index: 730

Text #14

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.8384. Min Act: -0.0000

Data Index: 1285500 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.7584. Min Act: -0.0001

Data Index: 808691 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.8551. Min Act: -0.0000

Data Index: 1204006 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.7823. Min Act: -0.0001

Data Index: 454330 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.7743. Min Act: -0.0000

Data Index: 829545 (C4 (Web Text))

Max Activating Token Index: 813

Text #19

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.7774. Min Act: -0.0001

Data Index: 568414 (C4 (Web Text))

Max Activating Token Index: 978