Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3652 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1988. Min Act: -0.0000

Data Index: 1158682 (C4 (Web Text))

Max Activating Token Index: 569

Text #1

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1858. Min Act: -0.0001

Data Index: 1304899 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1676. Min Act: -0.0000

Data Index: 1234645 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1721. Min Act: -0.0000

Data Index: 1040832 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1756. Min Act: -0.0000

Data Index: 688720 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1539. Min Act: -0.0000

Data Index: 457239 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1560. Min Act: -0.0000

Data Index: 1311167 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1557. Min Act: -0.0000

Data Index: 384102 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1554. Min Act: -0.0000

Data Index: 255466 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1553. Min Act: -0.0000

Data Index: 975835 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1453. Min Act: -0.0000

Data Index: 1337017 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1502. Min Act: -0.0000

Data Index: 755747 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1546. Min Act: -0.0001

Data Index: 1098255 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1474. Min Act: -0.0000

Data Index: 1218668 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1457. Min Act: -0.0000

Data Index: 1228451 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1355. Min Act: -0.0001

Data Index: 1143690 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1394. Min Act: -0.0000

Data Index: 1059964 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1395. Min Act: -0.0001

Data Index: 497358 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1383. Min Act: -0.0001

Data Index: 659713 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1324. Min Act: -0.0000

Data Index: 1127464 (C4 (Web Text))

Max Activating Token Index: 246