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

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

Neuron 4117 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: 4.1888. Min Range: -4.1888

Max Act: 4.1888. Min Act: -0.0000

Data Index: 726323 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 4.1888. Min Range: -4.1888

Max Act: 3.8760. Min Act: -0.0000

Data Index: 256239 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 4.1888. Min Range: -4.1888

Max Act: 4.1323. Min Act: -0.0001

Data Index: 247702 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 4.1888. Min Range: -4.1888

Max Act: 3.7909. Min Act: -0.0001

Data Index: 1151943 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 4.1888. Min Range: -4.1888

Max Act: 3.8159. Min Act: -0.0000

Data Index: 270832 (C4 (Web Text))

Max Activating Token Index: 769

Text #5

Max Range: 4.1888. Min Range: -4.1888

Max Act: 3.8884. Min Act: -0.0001

Data Index: 182614 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 4.1888. Min Range: -4.1888

Max Act: 3.8359. Min Act: -0.0001

Data Index: 34504 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 4.1888. Min Range: -4.1888

Max Act: 3.5329. Min Act: -0.0000

Data Index: 565024 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 4.1888. Min Range: -4.1888

Max Act: 3.7910. Min Act: -0.0001

Data Index: 767397 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 4.1888. Min Range: -4.1888

Max Act: 3.4172. Min Act: -0.0000

Data Index: 946692 (C4 (Web Text))

Max Activating Token Index: 823

Text #10

Max Range: 4.1888. Min Range: -4.1888

Max Act: 3.5517. Min Act: -0.0001

Data Index: 119569 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 4.1888. Min Range: -4.1888

Max Act: 3.4955. Min Act: -0.0000

Data Index: 682746 (C4 (Web Text))

Max Activating Token Index: 873

Text #12

Max Range: 4.1888. Min Range: -4.1888

Max Act: 3.3288. Min Act: -0.0000

Data Index: 427379 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 4.1888. Min Range: -4.1888

Max Act: 3.2526. Min Act: -0.0000

Data Index: 1247537 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 4.1888. Min Range: -4.1888

Max Act: 3.4176. Min Act: -0.0000

Data Index: 1032978 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 4.1888. Min Range: -4.1888

Max Act: 3.3879. Min Act: -0.0000

Data Index: 1342782 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 4.1888. Min Range: -4.1888

Max Act: 3.3342. Min Act: -0.0000

Data Index: 318980 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 4.1888. Min Range: -4.1888

Max Act: 3.2918. Min Act: -0.0000

Data Index: 1158897 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 4.1888. Min Range: -4.1888

Max Act: 3.2985. Min Act: -0.0001

Data Index: 813623 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 4.1888. Min Range: -4.1888

Max Act: 3.1695. Min Act: -0.0000

Data Index: 926453 (C4 (Web Text))

Max Activating Token Index: 139