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

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

Neuron 1000 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8091. Min Range: -1.8091

Max Act: 1.6971. Min Act: -0.0000

Data Index: 649628 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 1.8091. Min Range: -1.8091

Max Act: 1.7045. Min Act: -0.0000

Data Index: 907164 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 1.8091. Min Range: -1.8091

Max Act: 1.6531. Min Act: -0.0000

Data Index: 800899 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 1.8091. Min Range: -1.8091

Max Act: 1.5216. Min Act: -0.0000

Data Index: 773339 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 1.8091. Min Range: -1.8091

Max Act: 1.8091. Min Act: -0.0000

Data Index: 265045 (C4 (Web Text))

Max Activating Token Index: 795

Text #5

Max Range: 1.8091. Min Range: -1.8091

Max Act: 1.5833. Min Act: -0.0000

Data Index: 408709 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 1.8091. Min Range: -1.8091

Max Act: 1.5168. Min Act: -0.0000

Data Index: 198340 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 1.8091. Min Range: -1.8091

Max Act: 1.4959. Min Act: -0.0000

Data Index: 395705 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 1.8091. Min Range: -1.8091

Max Act: 1.4673. Min Act: -0.0000

Data Index: 1275499 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 1.8091. Min Range: -1.8091

Max Act: 1.4771. Min Act: -0.0000

Data Index: 707492 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 1.8091. Min Range: -1.8091

Max Act: 1.3761. Min Act: -0.0000

Data Index: 403071 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 1.8091. Min Range: -1.8091

Max Act: 1.4433. Min Act: -0.0000

Data Index: 327369 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 1.8091. Min Range: -1.8091

Max Act: 1.4401. Min Act: -0.0000

Data Index: 540750 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 1.8091. Min Range: -1.8091

Max Act: 1.5066. Min Act: -0.0000

Data Index: 816838 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 1.8091. Min Range: -1.8091

Max Act: 1.4328. Min Act: -0.0000

Data Index: 1131515 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 1.8091. Min Range: -1.8091

Max Act: 1.3311. Min Act: -0.0000

Data Index: 417061 (C4 (Web Text))

Max Activating Token Index: 466

Text #16

Max Range: 1.8091. Min Range: -1.8091

Max Act: 1.4111. Min Act: -0.0000

Data Index: 412696 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 1.8091. Min Range: -1.8091

Max Act: 1.4040. Min Act: -0.0000

Data Index: 369797 (C4 (Web Text))

Max Activating Token Index: 486

Text #18

Max Range: 1.8091. Min Range: -1.8091

Max Act: 1.5004. Min Act: -0.0000

Data Index: 1076393 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 1.8091. Min Range: -1.8091

Max Act: 1.2125. Min Act: -0.0000

Data Index: 859272 (C4 (Web Text))

Max Activating Token Index: 1018