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

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

Neuron 2415 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1791. Min Act: -0.0001

Data Index: 1114389 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1841. Min Act: -0.0001

Data Index: 77763 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1815. Min Act: -0.0001

Data Index: 26434 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1744. Min Act: -0.0001

Data Index: 547708 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1758. Min Act: -0.0001

Data Index: 845569 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1735. Min Act: -0.0001

Data Index: 885632 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1440. Min Act: -0.0001

Data Index: 655142 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1687. Min Act: -0.0001

Data Index: 1026238 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1627. Min Act: -0.0000

Data Index: 864351 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1556. Min Act: -0.0001

Data Index: 604504 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1446. Min Act: -0.0001

Data Index: 235007 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1458. Min Act: -0.0001

Data Index: 1264869 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1488. Min Act: -0.0001

Data Index: 174739 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1362. Min Act: -0.0000

Data Index: 1493370 (Python Code)

Max Activating Token Index: 368

Text #14

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1367. Min Act: -0.0001

Data Index: 501968 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1415. Min Act: -0.0000

Data Index: 1392953 (Python Code)

Max Activating Token Index: 466

Text #16

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1445. Min Act: -0.0000

Data Index: 1632520 (Python Code)

Max Activating Token Index: 434

Text #17

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1404. Min Act: -0.0001

Data Index: 244353 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1219. Min Act: -0.0001

Data Index: 1016117 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1222. Min Act: -0.0000

Data Index: 1650584 (Python Code)

Max Activating Token Index: 369