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

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

Neuron 5384 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: 3.0130. Min Range: -3.0130

Max Act: 3.0130. Min Act: -0.0000

Data Index: 990510 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 3.0130. Min Range: -3.0130

Max Act: 2.8479. Min Act: -0.0000

Data Index: 100341 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 3.0130. Min Range: -3.0130

Max Act: 2.8297. Min Act: -0.0000

Data Index: 1183125 (C4 (Web Text))

Max Activating Token Index: 239

Text #3

Max Range: 3.0130. Min Range: -3.0130

Max Act: 2.7989. Min Act: -0.0000

Data Index: 269787 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 3.0130. Min Range: -3.0130

Max Act: 2.8247. Min Act: -0.0000

Data Index: 1290943 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 3.0130. Min Range: -3.0130

Max Act: 2.4710. Min Act: -0.0000

Data Index: 1192806 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 3.0130. Min Range: -3.0130

Max Act: 2.4521. Min Act: -0.0000

Data Index: 392659 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 3.0130. Min Range: -3.0130

Max Act: 2.2111. Min Act: -0.0000

Data Index: 125672 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 3.0130. Min Range: -3.0130

Max Act: 2.2281. Min Act: -0.0000

Data Index: 395838 (C4 (Web Text))

Max Activating Token Index: 828

Text #9

Max Range: 3.0130. Min Range: -3.0130

Max Act: 1.8838. Min Act: -0.0000

Data Index: 1178066 (C4 (Web Text))

Max Activating Token Index: 966

Text #10

Max Range: 3.0130. Min Range: -3.0130

Max Act: 2.0158. Min Act: -0.0000

Data Index: 39149 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 3.0130. Min Range: -3.0130

Max Act: 2.1476. Min Act: -0.0000

Data Index: 26498 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 3.0130. Min Range: -3.0130

Max Act: 1.8689. Min Act: -0.0000

Data Index: 629189 (C4 (Web Text))

Max Activating Token Index: 955

Text #13

Max Range: 3.0130. Min Range: -3.0130

Max Act: 2.1433. Min Act: -0.0000

Data Index: 813530 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 3.0130. Min Range: -3.0130

Max Act: 1.9658. Min Act: -0.0000

Data Index: 25991 (C4 (Web Text))

Max Activating Token Index: 791

Text #15

Max Range: 3.0130. Min Range: -3.0130

Max Act: 1.8702. Min Act: -0.0000

Data Index: 621953 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 3.0130. Min Range: -3.0130

Max Act: 2.0092. Min Act: -0.0000

Data Index: 1326346 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 3.0130. Min Range: -3.0130

Max Act: 1.8246. Min Act: -0.0000

Data Index: 253356 (C4 (Web Text))

Max Activating Token Index: 354

Text #18

Max Range: 3.0130. Min Range: -3.0130

Max Act: 1.8040. Min Act: -0.0000

Data Index: 183685 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 3.0130. Min Range: -3.0130

Max Act: 1.7492. Min Act: -0.0000

Data Index: 849380 (C4 (Web Text))

Max Activating Token Index: 764