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

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

Neuron 3722 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9113. Min Range: -1.9113

Max Act: 1.9113. Min Act: -0.0000

Data Index: 1036922 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 1.9113. Min Range: -1.9113

Max Act: 1.5604. Min Act: -0.0000

Data Index: 291381 (C4 (Web Text))

Max Activating Token Index: 733

Text #2

Max Range: 1.9113. Min Range: -1.9113

Max Act: 1.6407. Min Act: -0.0000

Data Index: 513198 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 1.9113. Min Range: -1.9113

Max Act: 1.6350. Min Act: 0.0000

Data Index: 1130716 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 1.9113. Min Range: -1.9113

Max Act: 1.5280. Min Act: -0.0000

Data Index: 160230 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 1.9113. Min Range: -1.9113

Max Act: 1.5837. Min Act: -0.0000

Data Index: 637321 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 1.9113. Min Range: -1.9113

Max Act: 1.5851. Min Act: -0.0000

Data Index: 1291787 (C4 (Web Text))

Max Activating Token Index: 718

Text #7

Max Range: 1.9113. Min Range: -1.9113

Max Act: 1.5832. Min Act: 0.0000

Data Index: 758437 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 1.9113. Min Range: -1.9113

Max Act: 1.5705. Min Act: -0.0000

Data Index: 296334 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 1.9113. Min Range: -1.9113

Max Act: 1.5565. Min Act: -0.0000

Data Index: 908646 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 1.9113. Min Range: -1.9113

Max Act: 1.4503. Min Act: -0.0000

Data Index: 61165 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 1.9113. Min Range: -1.9113

Max Act: 1.5041. Min Act: -0.0000

Data Index: 358905 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 1.9113. Min Range: -1.9113

Max Act: 1.4931. Min Act: -0.0000

Data Index: 426307 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 1.9113. Min Range: -1.9113

Max Act: 1.4917. Min Act: -0.0000

Data Index: 1011012 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 1.9113. Min Range: -1.9113

Max Act: 1.4018. Min Act: -0.0000

Data Index: 431330 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 1.9113. Min Range: -1.9113

Max Act: 1.4286. Min Act: -0.0000

Data Index: 958371 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 1.9113. Min Range: -1.9113

Max Act: 1.3554. Min Act: -0.0000

Data Index: 276049 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 1.9113. Min Range: -1.9113

Max Act: 1.4311. Min Act: -0.0000

Data Index: 26154 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 1.9113. Min Range: -1.9113

Max Act: 1.4170. Min Act: -0.0000

Data Index: 853962 (C4 (Web Text))

Max Activating Token Index: 765

Text #19

Max Range: 1.9113. Min Range: -1.9113

Max Act: 1.3276. Min Act: -0.0000

Data Index: 997037 (C4 (Web Text))

Max Activating Token Index: 314