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

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

Neuron 5338 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1379. Min Range: -2.1379

Max Act: 2.1379. Min Act: -0.0000

Data Index: 1307632 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 2.1379. Min Range: -2.1379

Max Act: 2.0179. Min Act: -0.0000

Data Index: 985787 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 2.1379. Min Range: -2.1379

Max Act: 1.8746. Min Act: -0.0000

Data Index: 1331663 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 2.1379. Min Range: -2.1379

Max Act: 1.8607. Min Act: -0.0000

Data Index: 682826 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 2.1379. Min Range: -2.1379

Max Act: 1.7468. Min Act: -0.0000

Data Index: 700250 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 2.1379. Min Range: -2.1379

Max Act: 1.9289. Min Act: -0.0000

Data Index: 845364 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 2.1379. Min Range: -2.1379

Max Act: 1.8007. Min Act: -0.0001

Data Index: 1164987 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 2.1379. Min Range: -2.1379

Max Act: 1.8686. Min Act: -0.0000

Data Index: 502554 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 2.1379. Min Range: -2.1379

Max Act: 1.8315. Min Act: -0.0000

Data Index: 145068 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 2.1379. Min Range: -2.1379

Max Act: 1.6215. Min Act: -0.0000

Data Index: 990932 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 2.1379. Min Range: -2.1379

Max Act: 1.7518. Min Act: -0.0001

Data Index: 110514 (C4 (Web Text))

Max Activating Token Index: 385

Text #11

Max Range: 2.1379. Min Range: -2.1379

Max Act: 1.5141. Min Act: -0.0000

Data Index: 656480 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 2.1379. Min Range: -2.1379

Max Act: 1.5847. Min Act: -0.0000

Data Index: 1005139 (C4 (Web Text))

Max Activating Token Index: 433

Text #13

Max Range: 2.1379. Min Range: -2.1379

Max Act: 1.4948. Min Act: -0.0000

Data Index: 526257 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 2.1379. Min Range: -2.1379

Max Act: 1.5809. Min Act: -0.0000

Data Index: 1235008 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 2.1379. Min Range: -2.1379

Max Act: 1.6627. Min Act: -0.0000

Data Index: 21651 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 2.1379. Min Range: -2.1379

Max Act: 1.8424. Min Act: -0.0000

Data Index: 348917 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 2.1379. Min Range: -2.1379

Max Act: 1.5844. Min Act: -0.0000

Data Index: 1069527 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 2.1379. Min Range: -2.1379

Max Act: 1.7619. Min Act: -0.0000

Data Index: 128749 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 2.1379. Min Range: -2.1379

Max Act: 1.6363. Min Act: -0.0001

Data Index: 461772 (C4 (Web Text))

Max Activating Token Index: 117