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

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

Neuron 3312 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.7399. Min Act: -0.0000

Data Index: 1619086 (Python Code)

Max Activating Token Index: 136

Text #1

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.5440. Min Act: -0.0000

Data Index: 1587418 (Python Code)

Max Activating Token Index: 476

Text #2

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.4797. Min Act: -0.0000

Data Index: 1393549 (Python Code)

Max Activating Token Index: 759

Text #3

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.3741. Min Act: -0.0000

Data Index: 1558595 (Python Code)

Max Activating Token Index: 637

Text #4

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.4107. Min Act: -0.0000

Data Index: 1635716 (Python Code)

Max Activating Token Index: 557

Text #5

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.3336. Min Act: -0.0000

Data Index: 1585447 (Python Code)

Max Activating Token Index: 444

Text #6

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.3777. Min Act: -0.0000

Data Index: 425874 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.2998. Min Act: -0.0000

Data Index: 1586069 (Python Code)

Max Activating Token Index: 411

Text #8

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.3094. Min Act: -0.0000

Data Index: 1616360 (Python Code)

Max Activating Token Index: 444

Text #9

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.1367. Min Act: -0.0000

Data Index: 1513143 (Python Code)

Max Activating Token Index: 854

Text #10

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.0867. Min Act: -0.0000

Data Index: 1443972 (Python Code)

Max Activating Token Index: 301

Text #11

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.2490. Min Act: -0.0000

Data Index: 1412391 (Python Code)

Max Activating Token Index: 188

Text #12

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.2131. Min Act: -0.0000

Data Index: 792936 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.2442. Min Act: -0.0000

Data Index: 1543968 (Python Code)

Max Activating Token Index: 758

Text #14

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.1723. Min Act: -0.0000

Data Index: 87294 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.1646. Min Act: -0.0000

Data Index: 1394904 (Python Code)

Max Activating Token Index: 491

Text #16

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.1547. Min Act: -0.0000

Data Index: 1443203 (Python Code)

Max Activating Token Index: 863

Text #17

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.1329. Min Act: -0.0000

Data Index: 1607690 (Python Code)

Max Activating Token Index: 462

Text #18

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.0813. Min Act: -0.0000

Data Index: 1595897 (Python Code)

Max Activating Token Index: 360

Text #19

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.1339. Min Act: -0.0000

Data Index: 967876 (C4 (Web Text))

Max Activating Token Index: 222