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

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

Neuron 2822 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.9784. Min Act: -0.0000

Data Index: 669911 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.8913. Min Act: -0.0000

Data Index: 217365 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.8329. Min Act: -0.0000

Data Index: 271567 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.6349. Min Act: -0.0000

Data Index: 927718 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.7748. Min Act: -0.0000

Data Index: 889385 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.6846. Min Act: -0.0000

Data Index: 399624 (C4 (Web Text))

Max Activating Token Index: 577

Text #6

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.7035. Min Act: -0.0000

Data Index: 663857 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.7126. Min Act: -0.0000

Data Index: 550673 (C4 (Web Text))

Max Activating Token Index: 563

Text #8

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.6022. Min Act: -0.0000

Data Index: 1149132 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.7554. Min Act: -0.0000

Data Index: 1208749 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.6750. Min Act: -0.0000

Data Index: 932103 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.6152. Min Act: -0.0000

Data Index: 405430 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.6599. Min Act: -0.0000

Data Index: 741955 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.6154. Min Act: -0.0000

Data Index: 814876 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.6002. Min Act: -0.0000

Data Index: 259609 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.6351. Min Act: -0.0000

Data Index: 51826 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.6421. Min Act: -0.0000

Data Index: 1404614 (Python Code)

Max Activating Token Index: 424

Text #17

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.5941. Min Act: -0.0000

Data Index: 1273493 (C4 (Web Text))

Max Activating Token Index: 387

Text #18

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.6443. Min Act: -0.0000

Data Index: 671575 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.6729. Min Act: 0.0000

Data Index: 449791 (C4 (Web Text))

Max Activating Token Index: 231