Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5594 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.2537. Min Range: -3.2537

Max Act: 3.2414. Min Act: -0.0000

Data Index: 1442774 (Python Code)

Max Activating Token Index: 28

Text #1

Max Range: 3.2537. Min Range: -3.2537

Max Act: 3.2537. Min Act: -0.0000

Data Index: 100208 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 3.2537. Min Range: -3.2537

Max Act: 2.9147. Min Act: -0.0000

Data Index: 694710 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 3.2537. Min Range: -3.2537

Max Act: 2.6659. Min Act: -0.0000

Data Index: 1634658 (Python Code)

Max Activating Token Index: 282

Text #4

Max Range: 3.2537. Min Range: -3.2537

Max Act: 2.5456. Min Act: -0.0000

Data Index: 1411835 (Python Code)

Max Activating Token Index: 852

Text #5

Max Range: 3.2537. Min Range: -3.2537

Max Act: 2.6557. Min Act: -0.0000

Data Index: 1524631 (Python Code)

Max Activating Token Index: 441

Text #6

Max Range: 3.2537. Min Range: -3.2537

Max Act: 2.6537. Min Act: -0.0000

Data Index: 1417104 (Python Code)

Max Activating Token Index: 679

Text #7

Max Range: 3.2537. Min Range: -3.2537

Max Act: 2.4430. Min Act: -0.0000

Data Index: 1386828 (Python Code)

Max Activating Token Index: 890

Text #8

Max Range: 3.2537. Min Range: -3.2537

Max Act: 2.6000. Min Act: -0.0000

Data Index: 1547622 (Python Code)

Max Activating Token Index: 193

Text #9

Max Range: 3.2537. Min Range: -3.2537

Max Act: 2.5963. Min Act: -0.0000

Data Index: 1535129 (Python Code)

Max Activating Token Index: 52

Text #10

Max Range: 3.2537. Min Range: -3.2537

Max Act: 2.4485. Min Act: -0.0000

Data Index: 1625077 (Python Code)

Max Activating Token Index: 417

Text #11

Max Range: 3.2537. Min Range: -3.2537

Max Act: 2.4035. Min Act: -0.0000

Data Index: 1445264 (Python Code)

Max Activating Token Index: 663

Text #12

Max Range: 3.2537. Min Range: -3.2537

Max Act: 2.5107. Min Act: -0.0000

Data Index: 1543359 (Python Code)

Max Activating Token Index: 873

Text #13

Max Range: 3.2537. Min Range: -3.2537

Max Act: 2.3707. Min Act: -0.0000

Data Index: 1562234 (Python Code)

Max Activating Token Index: 241

Text #14

Max Range: 3.2537. Min Range: -3.2537

Max Act: 2.5013. Min Act: -0.0000

Data Index: 1397837 (Python Code)

Max Activating Token Index: 632

Text #15

Max Range: 3.2537. Min Range: -3.2537

Max Act: 2.5999. Min Act: -0.0000

Data Index: 1383739 (Python Code)

Max Activating Token Index: 152

Text #16

Max Range: 3.2537. Min Range: -3.2537

Max Act: 2.3535. Min Act: -0.0000

Data Index: 1434415 (Python Code)

Max Activating Token Index: 130

Text #17

Max Range: 3.2537. Min Range: -3.2537

Max Act: 2.5357. Min Act: -0.0000

Data Index: 1524180 (Python Code)

Max Activating Token Index: 427

Text #18

Max Range: 3.2537. Min Range: -3.2537

Max Act: 2.2618. Min Act: -0.0000

Data Index: 1525356 (Python Code)

Max Activating Token Index: 333

Text #19

Max Range: 3.2537. Min Range: -3.2537

Max Act: 2.3705. Min Act: -0.0000

Data Index: 1599934 (Python Code)

Max Activating Token Index: 5