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

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

Neuron 1616 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1839. Min Act: -0.0002

Data Index: 261058 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1700. Min Act: -0.0001

Data Index: 775702 (C4 (Web Text))

Max Activating Token Index: 770

Text #2

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1675. Min Act: -0.0001

Data Index: 97749 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1666. Min Act: -0.0002

Data Index: 1180684 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1605. Min Act: -0.0002

Data Index: 849583 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1606. Min Act: -0.0002

Data Index: 1322691 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1498. Min Act: -0.0002

Data Index: 385763 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1452. Min Act: -0.0001

Data Index: 36709 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1481. Min Act: -0.0001

Data Index: 985452 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1518. Min Act: -0.0002

Data Index: 1035498 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1350. Min Act: -0.0001

Data Index: 584056 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1400. Min Act: -0.0002

Data Index: 271835 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1430. Min Act: -0.0002

Data Index: 1269671 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1313. Min Act: -0.0002

Data Index: 1342269 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1383. Min Act: -0.0002

Data Index: 281742 (C4 (Web Text))

Max Activating Token Index: 477

Text #15

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1386. Min Act: -0.0002

Data Index: 342679 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1248. Min Act: -0.0002

Data Index: 642631 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1266. Min Act: -0.0002

Data Index: 200646 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1284. Min Act: -0.0002

Data Index: 261873 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1345. Min Act: -0.0001

Data Index: 1357942 (C4 (Web Text))

Max Activating Token Index: 251