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

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

Neuron 4650 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1623. Min Act: -0.0000

Data Index: 502247 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1123. Min Act: -0.0000

Data Index: 426015 (C4 (Web Text))

Max Activating Token Index: 940

Text #2

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.0950. Min Act: -0.0000

Data Index: 343977 (C4 (Web Text))

Max Activating Token Index: 532

Text #3

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.0712. Min Act: -0.0000

Data Index: 114437 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.0660. Min Act: -0.0000

Data Index: 1350900 (C4 (Web Text))

Max Activating Token Index: 397

Text #5

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.0629. Min Act: 0.0000

Data Index: 326604 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.0596. Min Act: -0.0000

Data Index: 1031608 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.0582. Min Act: -0.0000

Data Index: 1088661 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.0652. Min Act: -0.0000

Data Index: 1084174 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.0480. Min Act: -0.0000

Data Index: 1102480 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.0554. Min Act: -0.0000

Data Index: 1315908 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.0548. Min Act: -0.0000

Data Index: 903287 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.0460. Min Act: -0.0000

Data Index: 1080092 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.0384. Min Act: -0.0000

Data Index: 196353 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.0457. Min Act: -0.0000

Data Index: 33209 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.0472. Min Act: -0.0000

Data Index: 39227 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.0457. Min Act: -0.0000

Data Index: 820909 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.0508. Min Act: -0.0000

Data Index: 674202 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.0437. Min Act: -0.0000

Data Index: 109212 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.0315. Min Act: -0.0000

Data Index: 989886 (C4 (Web Text))

Max Activating Token Index: 16