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

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

Neuron 1566 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.7697. Min Act: 0.0000

Data Index: 622753 (C4 (Web Text))

Max Activating Token Index: 941

Text #1

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.7537. Min Act: -0.0000

Data Index: 1249388 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.6731. Min Act: -0.0000

Data Index: 725323 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.6885. Min Act: -0.0000

Data Index: 691198 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.6509. Min Act: -0.0000

Data Index: 1028962 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.6222. Min Act: -0.0000

Data Index: 276486 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.5988. Min Act: 0.0000

Data Index: 991978 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.5926. Min Act: 0.0001

Data Index: 818354 (C4 (Web Text))

Max Activating Token Index: 246

Text #8

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.5856. Min Act: -0.0000

Data Index: 166032 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.5637. Min Act: -0.0000

Data Index: 304011 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.5835. Min Act: -0.0000

Data Index: 1026620 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.5610. Min Act: -0.0001

Data Index: 789372 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.5556. Min Act: -0.0000

Data Index: 144475 (C4 (Web Text))

Max Activating Token Index: 450

Text #13

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.5522. Min Act: -0.0000

Data Index: 1085493 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.5516. Min Act: -0.0000

Data Index: 1223865 (C4 (Web Text))

Max Activating Token Index: 374

Text #15

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.5406. Min Act: -0.0001

Data Index: 254013 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.5263. Min Act: -0.0001

Data Index: 632291 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.5083. Min Act: -0.0000

Data Index: 382434 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.5036. Min Act: -0.0000

Data Index: 494762 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.5203. Min Act: -0.0001

Data Index: 514684 (C4 (Web Text))

Max Activating Token Index: 302