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

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

Neuron 967 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1730. Min Range: -1.1730

Max Act: 1.0942. Min Act: -0.0001

Data Index: 964466 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 1.1730. Min Range: -1.1730

Max Act: 1.1730. Min Act: -0.0001

Data Index: 115434 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 1.1730. Min Range: -1.1730

Max Act: 1.0632. Min Act: -0.0001

Data Index: 929033 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 1.1730. Min Range: -1.1730

Max Act: 1.0624. Min Act: -0.0001

Data Index: 1351234 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 1.1730. Min Range: -1.1730

Max Act: 1.0059. Min Act: -0.0001

Data Index: 20012 (C4 (Web Text))

Max Activating Token Index: 1019

Text #5

Max Range: 1.1730. Min Range: -1.1730

Max Act: 1.0532. Min Act: -0.0001

Data Index: 238235 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 1.1730. Min Range: -1.1730

Max Act: 1.0194. Min Act: -0.0001

Data Index: 429868 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 1.1730. Min Range: -1.1730

Max Act: 0.9287. Min Act: -0.0001

Data Index: 585913 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 1.1730. Min Range: -1.1730

Max Act: 1.0523. Min Act: -0.0001

Data Index: 316929 (C4 (Web Text))

Max Activating Token Index: 319

Text #9

Max Range: 1.1730. Min Range: -1.1730

Max Act: 1.0327. Min Act: -0.0001

Data Index: 1101625 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 1.1730. Min Range: -1.1730

Max Act: 0.9765. Min Act: -0.0001

Data Index: 633225 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 1.1730. Min Range: -1.1730

Max Act: 0.9907. Min Act: -0.0001

Data Index: 602136 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 1.1730. Min Range: -1.1730

Max Act: 0.9530. Min Act: -0.0001

Data Index: 82174 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 1.1730. Min Range: -1.1730

Max Act: 1.0021. Min Act: -0.0001

Data Index: 26565 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 1.1730. Min Range: -1.1730

Max Act: 0.9247. Min Act: -0.0001

Data Index: 1061319 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 1.1730. Min Range: -1.1730

Max Act: 0.8968. Min Act: -0.0001

Data Index: 401213 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 1.1730. Min Range: -1.1730

Max Act: 0.9808. Min Act: -0.0001

Data Index: 431261 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 1.1730. Min Range: -1.1730

Max Act: 0.9879. Min Act: -0.0001

Data Index: 465475 (C4 (Web Text))

Max Activating Token Index: 667

Text #18

Max Range: 1.1730. Min Range: -1.1730

Max Act: 0.9455. Min Act: -0.0001

Data Index: 223501 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 1.1730. Min Range: -1.1730

Max Act: 0.9348. Min Act: -0.0001

Data Index: 507869 (C4 (Web Text))

Max Activating Token Index: 181