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

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

Neuron 3756 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.9145. Min Act: -0.0000

Data Index: 1381576 (Python Code)

Max Activating Token Index: 287

Text #1

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.6730. Min Act: -0.0000

Data Index: 1521386 (Python Code)

Max Activating Token Index: 208

Text #2

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.8379. Min Act: -0.0000

Data Index: 1405681 (Python Code)

Max Activating Token Index: 219

Text #3

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7904. Min Act: -0.0000

Data Index: 1360531 (Python Code)

Max Activating Token Index: 399

Text #4

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7301. Min Act: -0.0000

Data Index: 1496073 (Python Code)

Max Activating Token Index: 953

Text #5

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7425. Min Act: -0.0000

Data Index: 1575282 (Python Code)

Max Activating Token Index: 550

Text #6

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7846. Min Act: -0.0000

Data Index: 1642430 (Python Code)

Max Activating Token Index: 227

Text #7

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.8072. Min Act: 0.0001

Data Index: 1430813 (Python Code)

Max Activating Token Index: 231

Text #8

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7370. Min Act: -0.0000

Data Index: 1629706 (Python Code)

Max Activating Token Index: 190

Text #9

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.6802. Min Act: 0.0001

Data Index: 1366067 (Python Code)

Max Activating Token Index: 906

Text #10

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.6496. Min Act: -0.0000

Data Index: 1519421 (Python Code)

Max Activating Token Index: 537

Text #11

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.6735. Min Act: 0.0002

Data Index: 1619822 (Python Code)

Max Activating Token Index: 927

Text #12

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.6349. Min Act: -0.0000

Data Index: 1400422 (Python Code)

Max Activating Token Index: 469

Text #13

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7028. Min Act: 0.0000

Data Index: 1654248 (Python Code)

Max Activating Token Index: 476

Text #14

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.6091. Min Act: -0.0000

Data Index: 1458930 (Python Code)

Max Activating Token Index: 607

Text #15

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.6515. Min Act: 0.0000

Data Index: 1468177 (Python Code)

Max Activating Token Index: 329

Text #16

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.6796. Min Act: 0.0002

Data Index: 1581484 (Python Code)

Max Activating Token Index: 996

Text #17

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.6445. Min Act: 0.0001

Data Index: 1494799 (Python Code)

Max Activating Token Index: 730

Text #18

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.6366. Min Act: 0.0001

Data Index: 1518316 (Python Code)

Max Activating Token Index: 123

Text #19

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.6671. Min Act: 0.0001

Data Index: 1420107 (Python Code)

Max Activating Token Index: 152