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

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

Neuron 3990 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1003. Min Range: -1.1003

Max Act: 1.1003. Min Act: -0.0001

Data Index: 1273667 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 1.1003. Min Range: -1.1003

Max Act: 1.0801. Min Act: -0.0000

Data Index: 311050 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 1.1003. Min Range: -1.1003

Max Act: 1.0989. Min Act: -0.0001

Data Index: 581737 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 1.1003. Min Range: -1.1003

Max Act: 1.0475. Min Act: -0.0000

Data Index: 1310063 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 1.1003. Min Range: -1.1003

Max Act: 1.0667. Min Act: -0.0001

Data Index: 514252 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 1.1003. Min Range: -1.1003

Max Act: 1.0538. Min Act: -0.0000

Data Index: 1002993 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 1.1003. Min Range: -1.1003

Max Act: 0.9947. Min Act: -0.0001

Data Index: 401485 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 1.1003. Min Range: -1.1003

Max Act: 0.9940. Min Act: -0.0000

Data Index: 347973 (C4 (Web Text))

Max Activating Token Index: 634

Text #8

Max Range: 1.1003. Min Range: -1.1003

Max Act: 1.0455. Min Act: -0.0001

Data Index: 1140084 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 1.1003. Min Range: -1.1003

Max Act: 0.9950. Min Act: -0.0000

Data Index: 444826 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 1.1003. Min Range: -1.1003

Max Act: 0.9980. Min Act: -0.0000

Data Index: 319336 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 1.1003. Min Range: -1.1003

Max Act: 0.9311. Min Act: -0.0001

Data Index: 753166 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 1.1003. Min Range: -1.1003

Max Act: 1.0121. Min Act: -0.0000

Data Index: 94827 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 1.1003. Min Range: -1.1003

Max Act: 0.8512. Min Act: -0.0001

Data Index: 723808 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 1.1003. Min Range: -1.1003

Max Act: 0.9015. Min Act: -0.0000

Data Index: 735161 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 1.1003. Min Range: -1.1003

Max Act: 0.9238. Min Act: -0.0001

Data Index: 143288 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 1.1003. Min Range: -1.1003

Max Act: 0.9245. Min Act: -0.0000

Data Index: 824639 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 1.1003. Min Range: -1.1003

Max Act: 0.8927. Min Act: -0.0000

Data Index: 31349 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 1.1003. Min Range: -1.1003

Max Act: 0.8892. Min Act: -0.0001

Data Index: 955141 (C4 (Web Text))

Max Activating Token Index: 910

Text #19

Max Range: 1.1003. Min Range: -1.1003

Max Act: 0.9038. Min Act: -0.0000

Data Index: 528057 (C4 (Web Text))

Max Activating Token Index: 25