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

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

Neuron 4709 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.9599. Min Act: -0.0000

Data Index: 785747 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.8168. Min Act: -0.0000

Data Index: 1653937 (Python Code)

Max Activating Token Index: 380

Text #2

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.8211. Min Act: -0.0000

Data Index: 1445674 (Python Code)

Max Activating Token Index: 490

Text #3

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.7989. Min Act: -0.0000

Data Index: 1610433 (Python Code)

Max Activating Token Index: 799

Text #4

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.7731. Min Act: -0.0000

Data Index: 1595521 (Python Code)

Max Activating Token Index: 260

Text #5

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.7500. Min Act: -0.0000

Data Index: 1414630 (Python Code)

Max Activating Token Index: 775

Text #6

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.7508. Min Act: -0.0000

Data Index: 1421590 (Python Code)

Max Activating Token Index: 546

Text #7

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.7999. Min Act: -0.0000

Data Index: 1479054 (Python Code)

Max Activating Token Index: 919

Text #8

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.7679. Min Act: -0.0000

Data Index: 1554497 (Python Code)

Max Activating Token Index: 233

Text #9

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.6936. Min Act: -0.0000

Data Index: 1197696 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.7227. Min Act: -0.0000

Data Index: 1496690 (Python Code)

Max Activating Token Index: 573

Text #11

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.6877. Min Act: -0.0000

Data Index: 1476937 (Python Code)

Max Activating Token Index: 441

Text #12

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.7034. Min Act: -0.0000

Data Index: 1301824 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.6518. Min Act: -0.0000

Data Index: 1510781 (Python Code)

Max Activating Token Index: 386

Text #14

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.7001. Min Act: -0.0000

Data Index: 1473860 (Python Code)

Max Activating Token Index: 957

Text #15

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.6674. Min Act: -0.0000

Data Index: 1497916 (Python Code)

Max Activating Token Index: 183

Text #16

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.6834. Min Act: -0.0000

Data Index: 833922 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.6379. Min Act: -0.0000

Data Index: 132153 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.6356. Min Act: -0.0000

Data Index: 1651603 (Python Code)

Max Activating Token Index: 944

Text #19

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.6635. Min Act: -0.0000

Data Index: 59774 (C4 (Web Text))

Max Activating Token Index: 22