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

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

Neuron 4040 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.4022. Min Act: -0.0000

Data Index: 345675 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.3633. Min Act: -0.0000

Data Index: 197524 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.2640. Min Act: -0.0000

Data Index: 166345 (C4 (Web Text))

Max Activating Token Index: 604

Text #3

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.2610. Min Act: -0.0000

Data Index: 792050 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.2366. Min Act: -0.0000

Data Index: 1035496 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.1742. Min Act: -0.0000

Data Index: 478318 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.2019. Min Act: -0.0000

Data Index: 916359 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.1909. Min Act: -0.0000

Data Index: 137571 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.1793. Min Act: -0.0000

Data Index: 1573478 (Python Code)

Max Activating Token Index: 999

Text #9

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.0999. Min Act: -0.0000

Data Index: 982006 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.0995. Min Act: -0.0000

Data Index: 657750 (C4 (Web Text))

Max Activating Token Index: 189

Text #11

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.0181. Min Act: -0.0000

Data Index: 1263332 (C4 (Web Text))

Max Activating Token Index: 736

Text #12

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.0874. Min Act: -0.0000

Data Index: 793591 (C4 (Web Text))

Max Activating Token Index: 558

Text #13

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.0238. Min Act: -0.0000

Data Index: 704435 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.0444. Min Act: -0.0000

Data Index: 1052086 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.0134. Min Act: -0.0000

Data Index: 545019 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.0325. Min Act: -0.0000

Data Index: 157372 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.0254. Min Act: -0.0000

Data Index: 1342223 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.0330. Min Act: -0.0000

Data Index: 615202 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 1.4022. Min Range: -1.4022

Max Act: 0.9976. Min Act: -0.0000

Data Index: 839998 (C4 (Web Text))

Max Activating Token Index: 399