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

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

Neuron 5595 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8531. Min Range: -3.8531

Max Act: 3.8531. Min Act: -0.0000

Data Index: 884083 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 3.8531. Min Range: -3.8531

Max Act: 3.8041. Min Act: -0.0000

Data Index: 565989 (C4 (Web Text))

Max Activating Token Index: 971

Text #2

Max Range: 3.8531. Min Range: -3.8531

Max Act: 3.8051. Min Act: -0.0000

Data Index: 529079 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 3.8531. Min Range: -3.8531

Max Act: 3.5366. Min Act: -0.0000

Data Index: 1141914 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 3.8531. Min Range: -3.8531

Max Act: 3.6284. Min Act: -0.0000

Data Index: 393704 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 3.8531. Min Range: -3.8531

Max Act: 3.4406. Min Act: -0.0000

Data Index: 35766 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 3.8531. Min Range: -3.8531

Max Act: 3.4129. Min Act: -0.0000

Data Index: 1053192 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 3.8531. Min Range: -3.8531

Max Act: 3.4087. Min Act: -0.0000

Data Index: 484414 (C4 (Web Text))

Max Activating Token Index: 488

Text #8

Max Range: 3.8531. Min Range: -3.8531

Max Act: 3.7052. Min Act: -0.0000

Data Index: 944798 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 3.8531. Min Range: -3.8531

Max Act: 3.5222. Min Act: -0.0000

Data Index: 95175 (C4 (Web Text))

Max Activating Token Index: 345

Text #10

Max Range: 3.8531. Min Range: -3.8531

Max Act: 3.5392. Min Act: -0.0000

Data Index: 630672 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 3.8531. Min Range: -3.8531

Max Act: 3.3670. Min Act: -0.0000

Data Index: 1199421 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 3.8531. Min Range: -3.8531

Max Act: 3.5195. Min Act: -0.0000

Data Index: 539919 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 3.8531. Min Range: -3.8531

Max Act: 3.5069. Min Act: -0.0000

Data Index: 1074957 (C4 (Web Text))

Max Activating Token Index: 447

Text #14

Max Range: 3.8531. Min Range: -3.8531

Max Act: 3.3463. Min Act: -0.0000

Data Index: 705648 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 3.8531. Min Range: -3.8531

Max Act: 3.3253. Min Act: -0.0000

Data Index: 301454 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 3.8531. Min Range: -3.8531

Max Act: 3.2914. Min Act: -0.0000

Data Index: 853428 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 3.8531. Min Range: -3.8531

Max Act: 3.4303. Min Act: -0.0000

Data Index: 1137311 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 3.8531. Min Range: -3.8531

Max Act: 3.4192. Min Act: -0.0000

Data Index: 568747 (C4 (Web Text))

Max Activating Token Index: 749

Text #19

Max Range: 3.8531. Min Range: -3.8531

Max Act: 3.4198. Min Act: -0.0000

Data Index: 489982 (C4 (Web Text))

Max Activating Token Index: 627