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

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

Neuron 2002 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1600. Min Act: -0.0000

Data Index: 116286 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1532. Min Act: -0.0000

Data Index: 1624694 (Python Code)

Max Activating Token Index: 829

Text #2

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1559. Min Act: -0.0000

Data Index: 1471359 (Python Code)

Max Activating Token Index: 938

Text #3

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1523. Min Act: -0.0000

Data Index: 531816 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1482. Min Act: -0.0000

Data Index: 539695 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1519. Min Act: -0.0000

Data Index: 223938 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1323. Min Act: -0.0000

Data Index: 1407506 (Python Code)

Max Activating Token Index: 990

Text #7

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1378. Min Act: -0.0000

Data Index: 428366 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1356. Min Act: -0.0000

Data Index: 401407 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1369. Min Act: -0.0000

Data Index: 579044 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1457. Min Act: -0.0000

Data Index: 1553116 (Python Code)

Max Activating Token Index: 427

Text #11

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1328. Min Act: -0.0000

Data Index: 760674 (C4 (Web Text))

Max Activating Token Index: 530

Text #12

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1361. Min Act: -0.0000

Data Index: 963783 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1359. Min Act: -0.0000

Data Index: 1018340 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1394. Min Act: -0.0000

Data Index: 107249 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1399. Min Act: -0.0000

Data Index: 1475909 (Python Code)

Max Activating Token Index: 426

Text #16

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1396. Min Act: -0.0000

Data Index: 396011 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1347. Min Act: -0.0000

Data Index: 1468240 (Python Code)

Max Activating Token Index: 773

Text #18

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1379. Min Act: -0.0000

Data Index: 1400682 (Python Code)

Max Activating Token Index: 376

Text #19

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1379. Min Act: -0.0000

Data Index: 1416919 (Python Code)

Max Activating Token Index: 915