Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1032 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1643. Min Act: -0.0001

Data Index: 646679 (C4 (Web Text))

Max Activating Token Index: 340

Text #1

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1676. Min Act: -0.0001

Data Index: 76218 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1650. Min Act: -0.0001

Data Index: 1123246 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1712. Min Act: -0.0000

Data Index: 1267457 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1692. Min Act: -0.0001

Data Index: 117777 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1553. Min Act: -0.0001

Data Index: 196098 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1540. Min Act: -0.0001

Data Index: 1146193 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1590. Min Act: -0.0001

Data Index: 431346 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1500. Min Act: -0.0001

Data Index: 735305 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1447. Min Act: -0.0001

Data Index: 147383 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1461. Min Act: -0.0001

Data Index: 1178777 (C4 (Web Text))

Max Activating Token Index: 801

Text #11

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1498. Min Act: -0.0001

Data Index: 1160144 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1437. Min Act: -0.0001

Data Index: 984359 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1557. Min Act: -0.0001

Data Index: 1274028 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1472. Min Act: -0.0001

Data Index: 604374 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1540. Min Act: -0.0001

Data Index: 65869 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1459. Min Act: -0.0001

Data Index: 316693 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1479. Min Act: -0.0001

Data Index: 685568 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1403. Min Act: -0.0001

Data Index: 874878 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1466. Min Act: -0.0001

Data Index: 199446 (C4 (Web Text))

Max Activating Token Index: 807