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

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

Neuron 4160 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: 0.4500. Min Range: -0.4500

Max Act: 0.4274. Min Act: -0.0001

Data Index: 75763 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.4500. Min Act: -0.0001

Data Index: 371595 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.4439. Min Act: -0.0002

Data Index: 323784 (C4 (Web Text))

Max Activating Token Index: 377

Text #3

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3833. Min Act: -0.0001

Data Index: 1224931 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3868. Min Act: -0.0001

Data Index: 790484 (C4 (Web Text))

Max Activating Token Index: 502

Text #5

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3827. Min Act: -0.0002

Data Index: 213983 (C4 (Web Text))

Max Activating Token Index: 990

Text #6

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.2991. Min Act: -0.0001

Data Index: 249846 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3236. Min Act: -0.0001

Data Index: 114393 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3044. Min Act: -0.0001

Data Index: 1032847 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3124. Min Act: -0.0001

Data Index: 653938 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.2842. Min Act: -0.0001

Data Index: 877903 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.2944. Min Act: -0.0001

Data Index: 1494934 (Python Code)

Max Activating Token Index: 19

Text #12

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3010. Min Act: -0.0001

Data Index: 863618 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3003. Min Act: -0.0001

Data Index: 814006 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.2774. Min Act: -0.0001

Data Index: 643965 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.2916. Min Act: -0.0001

Data Index: 815809 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.2701. Min Act: -0.0001

Data Index: 660105 (C4 (Web Text))

Max Activating Token Index: 259

Text #17

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.2859. Min Act: -0.0001

Data Index: 416727 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.2857. Min Act: -0.0001

Data Index: 235333 (C4 (Web Text))

Max Activating Token Index: 843

Text #19

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.2830. Min Act: -0.0001

Data Index: 798093 (C4 (Web Text))

Max Activating Token Index: 740