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

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

Neuron 1335 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0578. Min Act: -0.0003

Data Index: 447739 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0536. Min Act: -0.0003

Data Index: 1518818 (Python Code)

Max Activating Token Index: 121

Text #2

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0472. Min Act: -0.0003

Data Index: 1403512 (Python Code)

Max Activating Token Index: 866

Text #3

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0480. Min Act: -0.0003

Data Index: 1452741 (Python Code)

Max Activating Token Index: 149

Text #4

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0463. Min Act: -0.0003

Data Index: 1363919 (Python Code)

Max Activating Token Index: 172

Text #5

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0478. Min Act: -0.0003

Data Index: 714025 (C4 (Web Text))

Max Activating Token Index: 154

Text #6

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0464. Min Act: -0.0003

Data Index: 461619 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0475. Min Act: -0.0003

Data Index: 1204402 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0359. Min Act: -0.0003

Data Index: 1184441 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0489. Min Act: -0.0003

Data Index: 1618871 (Python Code)

Max Activating Token Index: 754

Text #10

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0449. Min Act: -0.0003

Data Index: 1469078 (Python Code)

Max Activating Token Index: 141

Text #11

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0469. Min Act: -0.0003

Data Index: 1601916 (Python Code)

Max Activating Token Index: 905

Text #12

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0449. Min Act: -0.0003

Data Index: 180817 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0423. Min Act: -0.0003

Data Index: 330052 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0442. Min Act: -0.0003

Data Index: 1292941 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0434. Min Act: -0.0003

Data Index: 1312558 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0454. Min Act: -0.0003

Data Index: 1201847 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0375. Min Act: -0.0003

Data Index: 581167 (C4 (Web Text))

Max Activating Token Index: 605

Text #18

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0473. Min Act: -0.0003

Data Index: 1465272 (Python Code)

Max Activating Token Index: 841

Text #19

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0450. Min Act: -0.0003

Data Index: 1421870 (Python Code)

Max Activating Token Index: 391