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

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

Neuron 3891 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.8466. Min Act: -0.0001

Data Index: 466514 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.7722. Min Act: -0.0000

Data Index: 1127527 (C4 (Web Text))

Max Activating Token Index: 859

Text #2

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.7181. Min Act: -0.0001

Data Index: 139764 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6077. Min Act: -0.0000

Data Index: 1288379 (C4 (Web Text))

Max Activating Token Index: 379

Text #4

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.5858. Min Act: -0.0000

Data Index: 81965 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6543. Min Act: -0.0000

Data Index: 1141923 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6484. Min Act: -0.0001

Data Index: 530273 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.5815. Min Act: -0.0000

Data Index: 333429 (C4 (Web Text))

Max Activating Token Index: 955

Text #8

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.5877. Min Act: -0.0000

Data Index: 592024 (C4 (Web Text))

Max Activating Token Index: 709

Text #9

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.5815. Min Act: -0.0000

Data Index: 636502 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.5503. Min Act: -0.0001

Data Index: 730566 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.5837. Min Act: -0.0000

Data Index: 971603 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.5567. Min Act: -0.0001

Data Index: 999046 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.5375. Min Act: -0.0000

Data Index: 477712 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.5499. Min Act: -0.0001

Data Index: 649958 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.5673. Min Act: -0.0000

Data Index: 215871 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.5138. Min Act: -0.0000

Data Index: 1166716 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.5274. Min Act: -0.0000

Data Index: 564669 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.5055. Min Act: -0.0000

Data Index: 1191090 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.4761. Min Act: -0.0000

Data Index: 735 (C4 (Web Text))

Max Activating Token Index: 835