Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1787 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.4854. Min Act: -0.0001

Data Index: 529168 (C4 (Web Text))

Max Activating Token Index: 281

Text #1

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.4156. Min Act: -0.0001

Data Index: 200746 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3814. Min Act: -0.0001

Data Index: 434838 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.4104. Min Act: -0.0001

Data Index: 705480 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3659. Min Act: -0.0001

Data Index: 1167679 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3207. Min Act: -0.0001

Data Index: 498860 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3505. Min Act: -0.0001

Data Index: 1248680 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3123. Min Act: -0.0001

Data Index: 726780 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3206. Min Act: -0.0001

Data Index: 658975 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3076. Min Act: -0.0001

Data Index: 740298 (C4 (Web Text))

Max Activating Token Index: 818

Text #10

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3254. Min Act: -0.0001

Data Index: 814035 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.2900. Min Act: -0.0001

Data Index: 1090299 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3211. Min Act: -0.0001

Data Index: 1027154 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.2919. Min Act: -0.0001

Data Index: 592733 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3064. Min Act: -0.0001

Data Index: 857507 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.2980. Min Act: -0.0001

Data Index: 389099 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.2980. Min Act: -0.0001

Data Index: 490849 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.2733. Min Act: -0.0001

Data Index: 138244 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.2845. Min Act: -0.0001

Data Index: 1100037 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.2766. Min Act: -0.0001

Data Index: 300755 (C4 (Web Text))

Max Activating Token Index: 96