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

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

Neuron 932 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2430. Min Act: -0.0001

Data Index: 1058535 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2360. Min Act: -0.0001

Data Index: 706789 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2265. Min Act: -0.0001

Data Index: 941816 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2161. Min Act: -0.0001

Data Index: 387586 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2212. Min Act: -0.0000

Data Index: 884419 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2053. Min Act: -0.0001

Data Index: 1002528 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1967. Min Act: -0.0001

Data Index: 1425059 (Python Code)

Max Activating Token Index: 32

Text #7

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1927. Min Act: -0.0001

Data Index: 523333 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2002. Min Act: -0.0001

Data Index: 686318 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2090. Min Act: -0.0000

Data Index: 1354182 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2048. Min Act: -0.0001

Data Index: 276236 (C4 (Web Text))

Max Activating Token Index: 340

Text #11

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1968. Min Act: -0.0001

Data Index: 763803 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1960. Min Act: -0.0001

Data Index: 329809 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1832. Min Act: -0.0001

Data Index: 1607976 (Python Code)

Max Activating Token Index: 575

Text #14

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1840. Min Act: -0.0001

Data Index: 1279099 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1844. Min Act: -0.0001

Data Index: 829894 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1844. Min Act: -0.0001

Data Index: 1050024 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1750. Min Act: -0.0000

Data Index: 631527 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1870. Min Act: -0.0000

Data Index: 499894 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1843. Min Act: -0.0001

Data Index: 301692 (C4 (Web Text))

Max Activating Token Index: 628