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

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

Neuron 3945 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.1021. Min Act: -0.0001

Data Index: 566245 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0943. Min Act: -0.0001

Data Index: 128547 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0948. Min Act: -0.0001

Data Index: 180064 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0886. Min Act: -0.0001

Data Index: 1247989 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0821. Min Act: -0.0001

Data Index: 455222 (C4 (Web Text))

Max Activating Token Index: 667

Text #5

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0810. Min Act: -0.0001

Data Index: 1110849 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0794. Min Act: -0.0001

Data Index: 500776 (C4 (Web Text))

Max Activating Token Index: 513

Text #7

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0810. Min Act: -0.0002

Data Index: 1655020 (Python Code)

Max Activating Token Index: 462

Text #8

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0791. Min Act: -0.0001

Data Index: 267282 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0799. Min Act: -0.0001

Data Index: 569030 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0802. Min Act: -0.0001

Data Index: 266728 (C4 (Web Text))

Max Activating Token Index: 653

Text #11

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0760. Min Act: -0.0001

Data Index: 699172 (C4 (Web Text))

Max Activating Token Index: 536

Text #12

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0751. Min Act: -0.0001

Data Index: 246981 (C4 (Web Text))

Max Activating Token Index: 993

Text #13

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0748. Min Act: -0.0001

Data Index: 989321 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0766. Min Act: -0.0001

Data Index: 1027303 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0746. Min Act: -0.0001

Data Index: 319898 (C4 (Web Text))

Max Activating Token Index: 712

Text #16

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0736. Min Act: -0.0001

Data Index: 737933 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0750. Min Act: -0.0001

Data Index: 405601 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0742. Min Act: -0.0001

Data Index: 1260644 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0746. Min Act: -0.0001

Data Index: 373134 (C4 (Web Text))

Max Activating Token Index: 547