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

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

Neuron 5503 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: 1.2975. Min Range: -1.2975

Max Act: 1.2975. Min Act: -0.0000

Data Index: 419950 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 1.2975. Min Range: -1.2975

Max Act: 1.0559. Min Act: -0.0000

Data Index: 649343 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 1.2975. Min Range: -1.2975

Max Act: 1.0488. Min Act: -0.0000

Data Index: 598439 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 1.2975. Min Range: -1.2975

Max Act: 1.0276. Min Act: -0.0000

Data Index: 779234 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 1.2975. Min Range: -1.2975

Max Act: 1.0203. Min Act: -0.0000

Data Index: 550970 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 1.2975. Min Range: -1.2975

Max Act: 1.0118. Min Act: -0.0000

Data Index: 6980 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 1.2975. Min Range: -1.2975

Max Act: 0.9176. Min Act: -0.0000

Data Index: 1098016 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 1.2975. Min Range: -1.2975

Max Act: 0.9164. Min Act: -0.0000

Data Index: 1111326 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 1.2975. Min Range: -1.2975

Max Act: 0.9340. Min Act: -0.0000

Data Index: 132302 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 1.2975. Min Range: -1.2975

Max Act: 0.8989. Min Act: -0.0000

Data Index: 1072432 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 1.2975. Min Range: -1.2975

Max Act: 0.8975. Min Act: -0.0000

Data Index: 833880 (C4 (Web Text))

Max Activating Token Index: 535

Text #11

Max Range: 1.2975. Min Range: -1.2975

Max Act: 0.9028. Min Act: -0.0000

Data Index: 523721 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 1.2975. Min Range: -1.2975

Max Act: 0.9003. Min Act: -0.0000

Data Index: 756717 (C4 (Web Text))

Max Activating Token Index: 634

Text #13

Max Range: 1.2975. Min Range: -1.2975

Max Act: 0.8525. Min Act: -0.0000

Data Index: 551553 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 1.2975. Min Range: -1.2975

Max Act: 0.8802. Min Act: -0.0000

Data Index: 1358369 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 1.2975. Min Range: -1.2975

Max Act: 0.8459. Min Act: -0.0000

Data Index: 898314 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 1.2975. Min Range: -1.2975

Max Act: 0.8294. Min Act: -0.0000

Data Index: 17372 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 1.2975. Min Range: -1.2975

Max Act: 0.7757. Min Act: -0.0000

Data Index: 142443 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 1.2975. Min Range: -1.2975

Max Act: 0.8162. Min Act: -0.0000

Data Index: 1140784 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 1.2975. Min Range: -1.2975

Max Act: 0.8626. Min Act: -0.0000

Data Index: 915812 (C4 (Web Text))

Max Activating Token Index: 190