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

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

Neuron 3213 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.9774. Min Act: -0.0000

Data Index: 194914 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.9097. Min Act: -0.0001

Data Index: 64800 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.9176. Min Act: -0.0001

Data Index: 873575 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.8219. Min Act: -0.0000

Data Index: 1170283 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.8443. Min Act: -0.0000

Data Index: 183198 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.8147. Min Act: -0.0001

Data Index: 948647 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.8245. Min Act: -0.0000

Data Index: 57920 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.8200. Min Act: -0.0001

Data Index: 195815 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.7101. Min Act: -0.0000

Data Index: 139676 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.7521. Min Act: -0.0001

Data Index: 858533 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.8038. Min Act: -0.0000

Data Index: 1326875 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.7794. Min Act: -0.0001

Data Index: 446630 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.8278. Min Act: -0.0001

Data Index: 1287855 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.8355. Min Act: -0.0001

Data Index: 355489 (C4 (Web Text))

Max Activating Token Index: 642

Text #14

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.8114. Min Act: -0.0000

Data Index: 795369 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.7862. Min Act: -0.0000

Data Index: 1256123 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.7551. Min Act: -0.0001

Data Index: 898389 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.7750. Min Act: -0.0000

Data Index: 659510 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.7454. Min Act: -0.0001

Data Index: 1105429 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.7270. Min Act: -0.0000

Data Index: 211814 (C4 (Web Text))

Max Activating Token Index: 29