Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5048 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2487. Min Act: -0.0000

Data Index: 231031 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2182. Min Act: -0.0000

Data Index: 853588 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2076. Min Act: -0.0000

Data Index: 140135 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2231. Min Act: -0.0000

Data Index: 761752 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2116. Min Act: -0.0001

Data Index: 96713 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2006. Min Act: -0.0001

Data Index: 1170782 (C4 (Web Text))

Max Activating Token Index: 555

Text #6

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1904. Min Act: -0.0000

Data Index: 590241 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2050. Min Act: -0.0001

Data Index: 812660 (C4 (Web Text))

Max Activating Token Index: 512

Text #8

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1901. Min Act: -0.0001

Data Index: 462134 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1584. Min Act: -0.0000

Data Index: 646951 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1722. Min Act: -0.0000

Data Index: 246255 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1628. Min Act: -0.0000

Data Index: 455762 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1871. Min Act: -0.0001

Data Index: 1163090 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1847. Min Act: -0.0000

Data Index: 503954 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1699. Min Act: -0.0000

Data Index: 33482 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1780. Min Act: -0.0000

Data Index: 369720 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1736. Min Act: -0.0000

Data Index: 919862 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1746. Min Act: -0.0000

Data Index: 261810 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1850. Min Act: -0.0000

Data Index: 251529 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1961. Min Act: -0.0000

Data Index: 1396211 (Python Code)

Max Activating Token Index: 217