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

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

Neuron 1587 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0728. Min Act: -0.0002

Data Index: 1241081 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0575. Min Act: -0.0002

Data Index: 12694 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0523. Min Act: -0.0002

Data Index: 275099 (C4 (Web Text))

Max Activating Token Index: 611

Text #3

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0522. Min Act: -0.0002

Data Index: 707758 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0552. Min Act: -0.0002

Data Index: 1045810 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0500. Min Act: -0.0002

Data Index: 1016677 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0496. Min Act: -0.0002

Data Index: 976931 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0506. Min Act: -0.0002

Data Index: 1062083 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0448. Min Act: -0.0002

Data Index: 356325 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0405. Min Act: -0.0002

Data Index: 1070669 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0427. Min Act: -0.0002

Data Index: 277615 (C4 (Web Text))

Max Activating Token Index: 885

Text #11

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0452. Min Act: -0.0002

Data Index: 283575 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0416. Min Act: -0.0002

Data Index: 1391189 (Python Code)

Max Activating Token Index: 1022

Text #13

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0444. Min Act: -0.0002

Data Index: 1271353 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0404. Min Act: -0.0002

Data Index: 1449603 (Python Code)

Max Activating Token Index: 640

Text #15

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0430. Min Act: -0.0002

Data Index: 1617575 (Python Code)

Max Activating Token Index: 638

Text #16

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1600837 (Python Code)

Max Activating Token Index: 310

Text #17

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0414. Min Act: -0.0002

Data Index: 1568281 (Python Code)

Max Activating Token Index: 603

Text #18

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0423. Min Act: -0.0002

Data Index: 1355081 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0428. Min Act: -0.0002

Data Index: 1476564 (Python Code)

Max Activating Token Index: 645