Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 245 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1764. Min Act: -0.0002

Data Index: 794963 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1755. Min Act: -0.0002

Data Index: 1179084 (C4 (Web Text))

Max Activating Token Index: 898

Text #2

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1875. Min Act: -0.0002

Data Index: 445244 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1735. Min Act: -0.0001

Data Index: 263255 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1608. Min Act: -0.0002

Data Index: 1142004 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1697. Min Act: -0.0002

Data Index: 535270 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1609. Min Act: -0.0002

Data Index: 651838 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1580. Min Act: -0.0002

Data Index: 233218 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1534. Min Act: -0.0002

Data Index: 1357895 (C4 (Web Text))

Max Activating Token Index: 954

Text #9

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1670. Min Act: -0.0001

Data Index: 1334911 (C4 (Web Text))

Max Activating Token Index: 522

Text #10

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1560. Min Act: -0.0002

Data Index: 421369 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1544. Min Act: -0.0002

Data Index: 888971 (C4 (Web Text))

Max Activating Token Index: 464

Text #12

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1531. Min Act: -0.0002

Data Index: 461081 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1515. Min Act: -0.0002

Data Index: 1192500 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1407. Min Act: -0.0001

Data Index: 1343033 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1550. Min Act: -0.0002

Data Index: 1014884 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1539. Min Act: -0.0001

Data Index: 1072942 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1435. Min Act: -0.0002

Data Index: 977292 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1508. Min Act: -0.0002

Data Index: 63700 (C4 (Web Text))

Max Activating Token Index: 248

Text #19

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1403. Min Act: -0.0002

Data Index: 826963 (C4 (Web Text))

Max Activating Token Index: 914