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

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

Neuron 241 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: 2.3305. Min Range: -2.3305

Max Act: 2.3305. Min Act: -0.0000

Data Index: 1592563 (Python Code)

Max Activating Token Index: 38

Text #1

Max Range: 2.3305. Min Range: -2.3305

Max Act: 1.9499. Min Act: -0.0000

Data Index: 1568493 (Python Code)

Max Activating Token Index: 209

Text #2

Max Range: 2.3305. Min Range: -2.3305

Max Act: 1.7599. Min Act: -0.0000

Data Index: 1404921 (Python Code)

Max Activating Token Index: 27

Text #3

Max Range: 2.3305. Min Range: -2.3305

Max Act: 1.7281. Min Act: -0.0000

Data Index: 1531057 (Python Code)

Max Activating Token Index: 1009

Text #4

Max Range: 2.3305. Min Range: -2.3305

Max Act: 1.5565. Min Act: -0.0000

Data Index: 1396747 (Python Code)

Max Activating Token Index: 744

Text #5

Max Range: 2.3305. Min Range: -2.3305

Max Act: 1.6750. Min Act: -0.0000

Data Index: 1564444 (Python Code)

Max Activating Token Index: 158

Text #6

Max Range: 2.3305. Min Range: -2.3305

Max Act: 1.5614. Min Act: -0.0000

Data Index: 1366576 (Python Code)

Max Activating Token Index: 89

Text #7

Max Range: 2.3305. Min Range: -2.3305

Max Act: 1.6664. Min Act: -0.0000

Data Index: 1458662 (Python Code)

Max Activating Token Index: 509

Text #8

Max Range: 2.3305. Min Range: -2.3305

Max Act: 1.6549. Min Act: -0.0000

Data Index: 1385385 (Python Code)

Max Activating Token Index: 770

Text #9

Max Range: 2.3305. Min Range: -2.3305

Max Act: 1.6224. Min Act: -0.0000

Data Index: 1555724 (Python Code)

Max Activating Token Index: 227

Text #10

Max Range: 2.3305. Min Range: -2.3305

Max Act: 1.6274. Min Act: -0.0000

Data Index: 1488791 (Python Code)

Max Activating Token Index: 479

Text #11

Max Range: 2.3305. Min Range: -2.3305

Max Act: 1.6110. Min Act: -0.0000

Data Index: 1379835 (Python Code)

Max Activating Token Index: 537

Text #12

Max Range: 2.3305. Min Range: -2.3305

Max Act: 1.4192. Min Act: -0.0000

Data Index: 1477389 (Python Code)

Max Activating Token Index: 193

Text #13

Max Range: 2.3305. Min Range: -2.3305

Max Act: 1.5761. Min Act: -0.0000

Data Index: 1623985 (Python Code)

Max Activating Token Index: 192

Text #14

Max Range: 2.3305. Min Range: -2.3305

Max Act: 1.4763. Min Act: -0.0000

Data Index: 1464051 (Python Code)

Max Activating Token Index: 367

Text #15

Max Range: 2.3305. Min Range: -2.3305

Max Act: 1.4679. Min Act: -0.0000

Data Index: 1437877 (Python Code)

Max Activating Token Index: 62

Text #16

Max Range: 2.3305. Min Range: -2.3305

Max Act: 1.4462. Min Act: -0.0000

Data Index: 1390730 (Python Code)

Max Activating Token Index: 258

Text #17

Max Range: 2.3305. Min Range: -2.3305

Max Act: 1.5575. Min Act: -0.0000

Data Index: 1596772 (Python Code)

Max Activating Token Index: 253

Text #18

Max Range: 2.3305. Min Range: -2.3305

Max Act: 1.4617. Min Act: -0.0000

Data Index: 1570476 (Python Code)

Max Activating Token Index: 769

Text #19

Max Range: 2.3305. Min Range: -2.3305

Max Act: 1.5122. Min Act: -0.0000

Data Index: 1520864 (Python Code)

Max Activating Token Index: 391