Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2537 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1640. Min Act: -0.0002

Data Index: 684745 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1620. Min Act: -0.0002

Data Index: 398848 (C4 (Web Text))

Max Activating Token Index: 633

Text #2

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1320. Min Act: -0.0002

Data Index: 868924 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1659. Min Act: -0.0002

Data Index: 979619 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1583. Min Act: -0.0002

Data Index: 624335 (C4 (Web Text))

Max Activating Token Index: 240

Text #5

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1620. Min Act: -0.0002

Data Index: 1243872 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1512. Min Act: -0.0002

Data Index: 31256 (C4 (Web Text))

Max Activating Token Index: 352

Text #7

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1402. Min Act: -0.0002

Data Index: 688624 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1439. Min Act: -0.0002

Data Index: 660806 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1485. Min Act: -0.0002

Data Index: 667130 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1367. Min Act: -0.0002

Data Index: 1201103 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1311. Min Act: -0.0002

Data Index: 869312 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1300. Min Act: -0.0002

Data Index: 1046700 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1162. Min Act: -0.0002

Data Index: 393410 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1344. Min Act: -0.0002

Data Index: 569011 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1295. Min Act: -0.0002

Data Index: 1021122 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.0990. Min Act: -0.0002

Data Index: 1020122 (C4 (Web Text))

Max Activating Token Index: 892

Text #17

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1221. Min Act: -0.0002

Data Index: 21626 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1258. Min Act: -0.0002

Data Index: 1245426 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1154. Min Act: -0.0002

Data Index: 220427 (C4 (Web Text))

Max Activating Token Index: 830