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

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

Neuron 3976 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: 0.2625. Min Range: -0.2625

Max Act: 0.2625. Min Act: -0.0000

Data Index: 549954 (C4 (Web Text))

Max Activating Token Index: 694

Text #1

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2254. Min Act: -0.0000

Data Index: 1147345 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1967. Min Act: -0.0000

Data Index: 290763 (C4 (Web Text))

Max Activating Token Index: 217

Text #3

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1858. Min Act: -0.0000

Data Index: 911743 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1912. Min Act: -0.0000

Data Index: 1116970 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1729. Min Act: -0.0000

Data Index: 1278752 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1621. Min Act: -0.0000

Data Index: 1134763 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1617. Min Act: -0.0000

Data Index: 450427 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1621. Min Act: -0.0000

Data Index: 570911 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1500. Min Act: -0.0000

Data Index: 542559 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1552. Min Act: -0.0000

Data Index: 1091753 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1505. Min Act: -0.0000

Data Index: 737984 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1502. Min Act: -0.0000

Data Index: 696672 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1496. Min Act: -0.0000

Data Index: 579206 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1501. Min Act: -0.0000

Data Index: 497203 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1426. Min Act: -0.0000

Data Index: 1178135 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1462. Min Act: -0.0000

Data Index: 630246 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1361. Min Act: -0.0000

Data Index: 311201 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1449. Min Act: -0.0000

Data Index: 35416 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1451. Min Act: -0.0000

Data Index: 1167413 (C4 (Web Text))

Max Activating Token Index: 430