Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4440 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.1025. Min Act: -0.0002

Data Index: 1423827 (Python Code)

Max Activating Token Index: 131

Text #1

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0897. Min Act: -0.0003

Data Index: 327029 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0895. Min Act: -0.0002

Data Index: 640184 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0837. Min Act: -0.0002

Data Index: 540444 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0810. Min Act: -0.0002

Data Index: 1072553 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0808. Min Act: -0.0002

Data Index: 1357234 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0843. Min Act: -0.0003

Data Index: 601219 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0779. Min Act: -0.0002

Data Index: 1342762 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0739. Min Act: -0.0002

Data Index: 1226433 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0760. Min Act: -0.0002

Data Index: 218106 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0790. Min Act: -0.0002

Data Index: 104916 (C4 (Web Text))

Max Activating Token Index: 698

Text #11

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0809. Min Act: -0.0002

Data Index: 960968 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0781. Min Act: -0.0002

Data Index: 258186 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0749. Min Act: -0.0002

Data Index: 1344857 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0781. Min Act: -0.0003

Data Index: 1321189 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0774. Min Act: -0.0002

Data Index: 98211 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0771. Min Act: -0.0002

Data Index: 286118 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0766. Min Act: -0.0002

Data Index: 301599 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0781. Min Act: -0.0002

Data Index: 909327 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0751. Min Act: -0.0002

Data Index: 516079 (C4 (Web Text))

Max Activating Token Index: 5