Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 859 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0909. Min Act: -0.0000

Data Index: 47591 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0957. Min Act: -0.0000

Data Index: 480957 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0942. Min Act: -0.0000

Data Index: 1449963 (Python Code)

Max Activating Token Index: 5

Text #3

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0901. Min Act: -0.0000

Data Index: 593817 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0902. Min Act: -0.0000

Data Index: 24503 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0890. Min Act: -0.0000

Data Index: 1116397 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0895. Min Act: -0.0000

Data Index: 670315 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0899. Min Act: -0.0000

Data Index: 710923 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0860. Min Act: -0.0000

Data Index: 298002 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0854. Min Act: -0.0000

Data Index: 1343491 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0855. Min Act: -0.0001

Data Index: 40903 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0847. Min Act: -0.0000

Data Index: 1271476 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0884. Min Act: -0.0000

Data Index: 1211299 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0846. Min Act: -0.0000

Data Index: 1244922 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0849. Min Act: -0.0000

Data Index: 192635 (C4 (Web Text))

Max Activating Token Index: 321

Text #15

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0860. Min Act: -0.0001

Data Index: 132768 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0824. Min Act: -0.0000

Data Index: 918378 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0817. Min Act: -0.0000

Data Index: 873056 (C4 (Web Text))

Max Activating Token Index: 398

Text #18

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0816. Min Act: -0.0000

Data Index: 976733 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0807. Min Act: -0.0000

Data Index: 153456 (C4 (Web Text))

Max Activating Token Index: 559