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

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

Neuron 1794 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2169. Min Range: -4.2169

Max Act: 3.6013. Min Act: -0.0000

Data Index: 949106 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 4.2169. Min Range: -4.2169

Max Act: 4.1241. Min Act: -0.0000

Data Index: 652534 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 4.2169. Min Range: -4.2169

Max Act: 4.2169. Min Act: -0.0000

Data Index: 236081 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 4.2169. Min Range: -4.2169

Max Act: 3.7423. Min Act: -0.0000

Data Index: 80532 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 4.2169. Min Range: -4.2169

Max Act: 3.9657. Min Act: -0.0000

Data Index: 55481 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 4.2169. Min Range: -4.2169

Max Act: 3.7973. Min Act: -0.0000

Data Index: 790998 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 4.2169. Min Range: -4.2169

Max Act: 3.8676. Min Act: -0.0000

Data Index: 483144 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 4.2169. Min Range: -4.2169

Max Act: 3.7925. Min Act: -0.0000

Data Index: 950673 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 4.2169. Min Range: -4.2169

Max Act: 3.9796. Min Act: -0.0000

Data Index: 451104 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 4.2169. Min Range: -4.2169

Max Act: 3.6127. Min Act: -0.0000

Data Index: 716658 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 4.2169. Min Range: -4.2169

Max Act: 3.7726. Min Act: -0.0000

Data Index: 452742 (C4 (Web Text))

Max Activating Token Index: 549

Text #11

Max Range: 4.2169. Min Range: -4.2169

Max Act: 3.8037. Min Act: -0.0000

Data Index: 671956 (C4 (Web Text))

Max Activating Token Index: 464

Text #12

Max Range: 4.2169. Min Range: -4.2169

Max Act: 3.8695. Min Act: -0.0000

Data Index: 592945 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 4.2169. Min Range: -4.2169

Max Act: 3.8010. Min Act: -0.0000

Data Index: 151128 (C4 (Web Text))

Max Activating Token Index: 415

Text #14

Max Range: 4.2169. Min Range: -4.2169

Max Act: 3.8129. Min Act: -0.0000

Data Index: 167081 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 4.2169. Min Range: -4.2169

Max Act: 3.7245. Min Act: -0.0000

Data Index: 476881 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 4.2169. Min Range: -4.2169

Max Act: 3.2843. Min Act: -0.0000

Data Index: 1306921 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 4.2169. Min Range: -4.2169

Max Act: 3.5803. Min Act: -0.0000

Data Index: 909879 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 4.2169. Min Range: -4.2169

Max Act: 3.3959. Min Act: -0.0000

Data Index: 846328 (C4 (Web Text))

Max Activating Token Index: 574

Text #19

Max Range: 4.2169. Min Range: -4.2169

Max Act: 3.4825. Min Act: -0.0000

Data Index: 135424 (C4 (Web Text))

Max Activating Token Index: 567