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

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

Neuron 5094 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.3142. Min Act: -0.0001

Data Index: 1169370 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.3291. Min Act: -0.0001

Data Index: 445774 (C4 (Web Text))

Max Activating Token Index: 799

Text #2

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.2646. Min Act: -0.0001

Data Index: 636579 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.2592. Min Act: -0.0001

Data Index: 457452 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.2554. Min Act: -0.0001

Data Index: 863885 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.2468. Min Act: -0.0001

Data Index: 161511 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.1693. Min Act: -0.0001

Data Index: 783141 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.2235. Min Act: -0.0001

Data Index: 91800 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.1892. Min Act: -0.0001

Data Index: 1236259 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.1785. Min Act: -0.0001

Data Index: 73825 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.1072. Min Act: -0.0001

Data Index: 899022 (C4 (Web Text))

Max Activating Token Index: 732

Text #11

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.1787. Min Act: -0.0001

Data Index: 265788 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.0999. Min Act: -0.0001

Data Index: 422391 (C4 (Web Text))

Max Activating Token Index: 357

Text #13

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.0665. Min Act: -0.0001

Data Index: 193302 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.1695. Min Act: -0.0001

Data Index: 479556 (C4 (Web Text))

Max Activating Token Index: 538

Text #15

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.1812. Min Act: -0.0001

Data Index: 1335747 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.1615. Min Act: -0.0001

Data Index: 342580 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.1703. Min Act: -0.0001

Data Index: 765793 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.1262. Min Act: -0.0001

Data Index: 101988 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.0981. Min Act: -0.0001

Data Index: 811237 (C4 (Web Text))

Max Activating Token Index: 646