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

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

Neuron 3366 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.5677. Min Act: -0.0000

Data Index: 1226055 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4064. Min Act: -0.0000

Data Index: 182265 (C4 (Web Text))

Max Activating Token Index: 609

Text #2

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4470. Min Act: -0.0001

Data Index: 1203955 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4113. Min Act: -0.0000

Data Index: 1046461 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4142. Min Act: -0.0000

Data Index: 151321 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.3730. Min Act: -0.0000

Data Index: 206628 (C4 (Web Text))

Max Activating Token Index: 469

Text #6

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4309. Min Act: -0.0000

Data Index: 6669 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.3924. Min Act: -0.0000

Data Index: 821334 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.3638. Min Act: -0.0000

Data Index: 52927 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.3382. Min Act: -0.0000

Data Index: 182096 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.3715. Min Act: -0.0000

Data Index: 1289744 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.3843. Min Act: -0.0000

Data Index: 432516 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.3811. Min Act: -0.0000

Data Index: 546268 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.3404. Min Act: -0.0000

Data Index: 1344016 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.3571. Min Act: -0.0000

Data Index: 833803 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.3475. Min Act: -0.0001

Data Index: 106535 (C4 (Web Text))

Max Activating Token Index: 488

Text #16

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.3541. Min Act: -0.0000

Data Index: 1000858 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.2866. Min Act: -0.0000

Data Index: 1339201 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.3290. Min Act: -0.0000

Data Index: 635430 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.3292. Min Act: -0.0000

Data Index: 347887 (C4 (Web Text))

Max Activating Token Index: 224