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

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

Neuron 2655 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: 0.1719. Min Range: -0.1719

Max Act: 0.1543. Min Act: -0.0000

Data Index: 731349 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1632. Min Act: -0.0000

Data Index: 907426 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1638. Min Act: -0.0000

Data Index: 402600 (C4 (Web Text))

Max Activating Token Index: 482

Text #3

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1520. Min Act: -0.0000

Data Index: 1653337 (Python Code)

Max Activating Token Index: 195

Text #4

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1719. Min Act: -0.0000

Data Index: 176591 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1483. Min Act: -0.0000

Data Index: 574424 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1574. Min Act: -0.0000

Data Index: 296345 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1640. Min Act: -0.0000

Data Index: 155875 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1519. Min Act: -0.0000

Data Index: 183065 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1550. Min Act: -0.0000

Data Index: 188359 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1530. Min Act: -0.0000

Data Index: 353491 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1376. Min Act: -0.0000

Data Index: 191484 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1495. Min Act: -0.0000

Data Index: 6956 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1484. Min Act: -0.0000

Data Index: 63937 (C4 (Web Text))

Max Activating Token Index: 730

Text #14

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1426. Min Act: -0.0000

Data Index: 427899 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1473. Min Act: -0.0000

Data Index: 1232031 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1328. Min Act: -0.0000

Data Index: 399414 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1359. Min Act: -0.0000

Data Index: 1113860 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1374. Min Act: -0.0000

Data Index: 524211 (C4 (Web Text))

Max Activating Token Index: 587

Text #19

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1375. Min Act: -0.0000

Data Index: 1271870 (C4 (Web Text))

Max Activating Token Index: 4