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

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

Neuron 3232 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0957. Min Act: -0.0001

Data Index: 559563 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.1069. Min Act: -0.0001

Data Index: 315981 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.1043. Min Act: -0.0001

Data Index: 1291621 (C4 (Web Text))

Max Activating Token Index: 426

Text #3

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0946. Min Act: -0.0001

Data Index: 683164 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0862. Min Act: -0.0001

Data Index: 604241 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0907. Min Act: -0.0001

Data Index: 490582 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0936. Min Act: -0.0001

Data Index: 370360 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0809. Min Act: -0.0001

Data Index: 871789 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0743. Min Act: -0.0001

Data Index: 522270 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0719. Min Act: -0.0001

Data Index: 431714 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0752. Min Act: -0.0001

Data Index: 218293 (C4 (Web Text))

Max Activating Token Index: 628

Text #11

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0729. Min Act: -0.0001

Data Index: 350904 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0667. Min Act: -0.0001

Data Index: 738341 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0721. Min Act: -0.0001

Data Index: 790787 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0693. Min Act: -0.0001

Data Index: 72988 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0771. Min Act: -0.0001

Data Index: 405112 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0727. Min Act: -0.0001

Data Index: 1017935 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0715. Min Act: -0.0001

Data Index: 292968 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0662. Min Act: -0.0001

Data Index: 790894 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0691. Min Act: -0.0001

Data Index: 818444 (C4 (Web Text))

Max Activating Token Index: 127