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

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

Neuron 3520 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6928. Min Range: -2.6928

Max Act: 2.4945. Min Act: -0.0000

Data Index: 665480 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 2.6928. Min Range: -2.6928

Max Act: 2.4672. Min Act: -0.0000

Data Index: 117029 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 2.6928. Min Range: -2.6928

Max Act: 2.6928. Min Act: -0.0000

Data Index: 97190 (C4 (Web Text))

Max Activating Token Index: 579

Text #3

Max Range: 2.6928. Min Range: -2.6928

Max Act: 2.2412. Min Act: -0.0000

Data Index: 1315325 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 2.6928. Min Range: -2.6928

Max Act: 2.2229. Min Act: -0.0000

Data Index: 772902 (C4 (Web Text))

Max Activating Token Index: 468

Text #5

Max Range: 2.6928. Min Range: -2.6928

Max Act: 2.0627. Min Act: -0.0000

Data Index: 918100 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 2.6928. Min Range: -2.6928

Max Act: 2.0815. Min Act: -0.0000

Data Index: 1179853 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 2.6928. Min Range: -2.6928

Max Act: 1.6463. Min Act: -0.0000

Data Index: 839665 (C4 (Web Text))

Max Activating Token Index: 375

Text #8

Max Range: 2.6928. Min Range: -2.6928

Max Act: 1.9226. Min Act: -0.0000

Data Index: 641105 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 2.6928. Min Range: -2.6928

Max Act: 1.8336. Min Act: -0.0000

Data Index: 1035455 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 2.6928. Min Range: -2.6928

Max Act: 1.9969. Min Act: -0.0000

Data Index: 1026230 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 2.6928. Min Range: -2.6928

Max Act: 1.9895. Min Act: -0.0000

Data Index: 265251 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 2.6928. Min Range: -2.6928

Max Act: 1.8934. Min Act: -0.0000

Data Index: 1178345 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 2.6928. Min Range: -2.6928

Max Act: 1.8722. Min Act: -0.0000

Data Index: 1324011 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 2.6928. Min Range: -2.6928

Max Act: 1.8653. Min Act: -0.0000

Data Index: 531577 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 2.6928. Min Range: -2.6928

Max Act: 1.8212. Min Act: -0.0000

Data Index: 579219 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 2.6928. Min Range: -2.6928

Max Act: 1.8133. Min Act: -0.0000

Data Index: 1305302 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 2.6928. Min Range: -2.6928

Max Act: 1.9091. Min Act: -0.0000

Data Index: 393922 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 2.6928. Min Range: -2.6928

Max Act: 1.8043. Min Act: -0.0000

Data Index: 705979 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 2.6928. Min Range: -2.6928

Max Act: 1.8762. Min Act: -0.0000

Data Index: 544633 (C4 (Web Text))

Max Activating Token Index: 763