Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3865 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0035. Min Act: -0.0003

Data Index: 1325304 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0024. Min Act: -0.0003

Data Index: 752470 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0033. Min Act: -0.0004

Data Index: 546337 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0030. Min Act: -0.0003

Data Index: 1231791 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0026. Min Act: -0.0003

Data Index: 311598 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0025. Min Act: -0.0003

Data Index: 571748 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0027. Min Act: -0.0003

Data Index: 789562 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0025. Min Act: -0.0003

Data Index: 199865 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0023. Min Act: -0.0004

Data Index: 1332193 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0025. Min Act: -0.0003

Data Index: 747892 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0026. Min Act: -0.0003

Data Index: 838411 (C4 (Web Text))

Max Activating Token Index: 761

Text #11

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0026. Min Act: -0.0003

Data Index: 584376 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0019. Min Act: -0.0003

Data Index: 597445 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0019. Min Act: -0.0003

Data Index: 367955 (C4 (Web Text))

Max Activating Token Index: 980

Text #14

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0021. Min Act: -0.0003

Data Index: 1080727 (C4 (Web Text))

Max Activating Token Index: 212

Text #15

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0022. Min Act: -0.0003

Data Index: 1056792 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0026. Min Act: -0.0003

Data Index: 647510 (C4 (Web Text))

Max Activating Token Index: 561

Text #17

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0019. Min Act: -0.0003

Data Index: 847647 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0022. Min Act: -0.0003

Data Index: 1040203 (C4 (Web Text))

Max Activating Token Index: 1021

Text #19

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0019. Min Act: -0.0003

Data Index: 352781 (C4 (Web Text))

Max Activating Token Index: 653