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

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

Neuron 2031 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.7705. Min Act: -0.0001

Data Index: 840731 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.7132. Min Act: -0.0001

Data Index: 428581 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.6845. Min Act: -0.0001

Data Index: 570833 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.6988. Min Act: -0.0001

Data Index: 782780 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.6357. Min Act: -0.0001

Data Index: 745920 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.6250. Min Act: -0.0001

Data Index: 446247 (C4 (Web Text))

Max Activating Token Index: 948

Text #6

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.5997. Min Act: -0.0001

Data Index: 693283 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.5733. Min Act: -0.0001

Data Index: 198720 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.5507. Min Act: -0.0001

Data Index: 316902 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.5534. Min Act: -0.0001

Data Index: 14081 (C4 (Web Text))

Max Activating Token Index: 296

Text #10

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.5425. Min Act: -0.0001

Data Index: 1075477 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.6296. Min Act: -0.0001

Data Index: 615483 (C4 (Web Text))

Max Activating Token Index: 678

Text #12

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.5631. Min Act: -0.0001

Data Index: 1023266 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.5778. Min Act: -0.0001

Data Index: 298914 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.5389. Min Act: -0.0001

Data Index: 1074007 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.5372. Min Act: -0.0001

Data Index: 721626 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.5687. Min Act: -0.0001

Data Index: 79704 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.5306. Min Act: -0.0001

Data Index: 1085859 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.5417. Min Act: -0.0001

Data Index: 1072838 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.5228. Min Act: -0.0001

Data Index: 763196 (C4 (Web Text))

Max Activating Token Index: 95