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

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

Neuron 5056 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0834. Min Range: -1.0834

Max Act: 1.0834. Min Act: -0.0000

Data Index: 580475 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 1.0834. Min Range: -1.0834

Max Act: 0.9978. Min Act: -0.0000

Data Index: 650698 (C4 (Web Text))

Max Activating Token Index: 549

Text #2

Max Range: 1.0834. Min Range: -1.0834

Max Act: 0.8618. Min Act: -0.0000

Data Index: 863242 (C4 (Web Text))

Max Activating Token Index: 661

Text #3

Max Range: 1.0834. Min Range: -1.0834

Max Act: 0.9222. Min Act: -0.0000

Data Index: 894019 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 1.0834. Min Range: -1.0834

Max Act: 0.8915. Min Act: -0.0001

Data Index: 556897 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 1.0834. Min Range: -1.0834

Max Act: 0.8619. Min Act: -0.0001

Data Index: 62480 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 1.0834. Min Range: -1.0834

Max Act: 0.9011. Min Act: -0.0000

Data Index: 449865 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 1.0834. Min Range: -1.0834

Max Act: 0.8501. Min Act: -0.0000

Data Index: 437980 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 1.0834. Min Range: -1.0834

Max Act: 0.8116. Min Act: -0.0000

Data Index: 628196 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 1.0834. Min Range: -1.0834

Max Act: 0.8913. Min Act: -0.0001

Data Index: 332857 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 1.0834. Min Range: -1.0834

Max Act: 0.7909. Min Act: -0.0001

Data Index: 721336 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 1.0834. Min Range: -1.0834

Max Act: 0.8729. Min Act: -0.0001

Data Index: 963480 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 1.0834. Min Range: -1.0834

Max Act: 0.8467. Min Act: -0.0001

Data Index: 1243923 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 1.0834. Min Range: -1.0834

Max Act: 0.7891. Min Act: -0.0000

Data Index: 238967 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 1.0834. Min Range: -1.0834

Max Act: 0.7852. Min Act: -0.0001

Data Index: 165058 (C4 (Web Text))

Max Activating Token Index: 731

Text #15

Max Range: 1.0834. Min Range: -1.0834

Max Act: 0.8265. Min Act: -0.0000

Data Index: 385591 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 1.0834. Min Range: -1.0834

Max Act: 0.8466. Min Act: -0.0001

Data Index: 1203210 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 1.0834. Min Range: -1.0834

Max Act: 0.7932. Min Act: -0.0000

Data Index: 471939 (C4 (Web Text))

Max Activating Token Index: 696

Text #18

Max Range: 1.0834. Min Range: -1.0834

Max Act: 0.7539. Min Act: -0.0000

Data Index: 1348524 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 1.0834. Min Range: -1.0834

Max Act: 0.7646. Min Act: -0.0001

Data Index: 1004925 (C4 (Web Text))

Max Activating Token Index: 733