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

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

Neuron 4602 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.7696. Min Act: -0.0000

Data Index: 915163 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.6961. Min Act: -0.0000

Data Index: 1618837 (Python Code)

Max Activating Token Index: 785

Text #2

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.6928. Min Act: -0.0000

Data Index: 1390556 (Python Code)

Max Activating Token Index: 348

Text #3

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.6928. Min Act: -0.0000

Data Index: 1471702 (Python Code)

Max Activating Token Index: 646

Text #4

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.6672. Min Act: -0.0000

Data Index: 1077749 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.6507. Min Act: -0.0000

Data Index: 1441951 (Python Code)

Max Activating Token Index: 728

Text #6

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.6308. Min Act: -0.0000

Data Index: 1540750 (Python Code)

Max Activating Token Index: 739

Text #7

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.6144. Min Act: -0.0000

Data Index: 1494056 (Python Code)

Max Activating Token Index: 119

Text #8

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.6224. Min Act: -0.0000

Data Index: 793740 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.6514. Min Act: -0.0000

Data Index: 1584761 (Python Code)

Max Activating Token Index: 337

Text #10

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.5891. Min Act: -0.0000

Data Index: 519589 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.5914. Min Act: -0.0000

Data Index: 1429825 (Python Code)

Max Activating Token Index: 603

Text #12

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.6038. Min Act: -0.0000

Data Index: 1554364 (Python Code)

Max Activating Token Index: 40

Text #13

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.6339. Min Act: -0.0000

Data Index: 1396066 (Python Code)

Max Activating Token Index: 866

Text #14

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.6335. Min Act: -0.0000

Data Index: 1418309 (Python Code)

Max Activating Token Index: 827

Text #15

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.5725. Min Act: -0.0000

Data Index: 1497894 (Python Code)

Max Activating Token Index: 236

Text #16

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.5882. Min Act: -0.0000

Data Index: 413743 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.6110. Min Act: -0.0000

Data Index: 1599996 (Python Code)

Max Activating Token Index: 102

Text #18

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.5484. Min Act: -0.0000

Data Index: 1387744 (Python Code)

Max Activating Token Index: 724

Text #19

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.5745. Min Act: -0.0000

Data Index: 1468723 (Python Code)

Max Activating Token Index: 987