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

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

Neuron 125 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.8491. Min Act: -0.0000

Data Index: 1361067 (Python Code)

Max Activating Token Index: 932

Text #1

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.7039. Min Act: -0.0000

Data Index: 1530771 (Python Code)

Max Activating Token Index: 804

Text #2

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.6362. Min Act: -0.0000

Data Index: 1503831 (Python Code)

Max Activating Token Index: 802

Text #3

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.6446. Min Act: -0.0000

Data Index: 1561800 (Python Code)

Max Activating Token Index: 477

Text #4

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.6570. Min Act: -0.0000

Data Index: 1629728 (Python Code)

Max Activating Token Index: 1003

Text #5

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.5405. Min Act: -0.0000

Data Index: 1371434 (Python Code)

Max Activating Token Index: 963

Text #6

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.6521. Min Act: -0.0000

Data Index: 1589067 (Python Code)

Max Activating Token Index: 793

Text #7

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.6184. Min Act: -0.0000

Data Index: 1429526 (Python Code)

Max Activating Token Index: 582

Text #8

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.6116. Min Act: -0.0000

Data Index: 1643406 (Python Code)

Max Activating Token Index: 957

Text #9

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.5613. Min Act: -0.0000

Data Index: 1367861 (Python Code)

Max Activating Token Index: 453

Text #10

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.5663. Min Act: -0.0000

Data Index: 1437778 (Python Code)

Max Activating Token Index: 49

Text #11

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.5377. Min Act: -0.0000

Data Index: 1481936 (Python Code)

Max Activating Token Index: 557

Text #12

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.5498. Min Act: -0.0000

Data Index: 1524703 (Python Code)

Max Activating Token Index: 722

Text #13

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.4993. Min Act: -0.0000

Data Index: 1384989 (Python Code)

Max Activating Token Index: 319

Text #14

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.5105. Min Act: -0.0000

Data Index: 1582703 (Python Code)

Max Activating Token Index: 374

Text #15

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.5011. Min Act: -0.0000

Data Index: 1475045 (Python Code)

Max Activating Token Index: 685

Text #16

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.5328. Min Act: -0.0000

Data Index: 1517738 (Python Code)

Max Activating Token Index: 786

Text #17

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.5056. Min Act: -0.0000

Data Index: 1410725 (Python Code)

Max Activating Token Index: 1015

Text #18

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.4979. Min Act: -0.0000

Data Index: 1517221 (Python Code)

Max Activating Token Index: 349

Text #19

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.4969. Min Act: -0.0000

Data Index: 1590872 (Python Code)

Max Activating Token Index: 633