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

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

Neuron 5647 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.7999. Min Act: -0.0000

Data Index: 1433580 (Python Code)

Max Activating Token Index: 41

Text #1

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.7891. Min Act: -0.0000

Data Index: 1483397 (Python Code)

Max Activating Token Index: 441

Text #2

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.7100. Min Act: -0.0000

Data Index: 1574460 (Python Code)

Max Activating Token Index: 501

Text #3

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.7139. Min Act: -0.0000

Data Index: 1412127 (Python Code)

Max Activating Token Index: 521

Text #4

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.7496. Min Act: -0.0000

Data Index: 1480136 (Python Code)

Max Activating Token Index: 750

Text #5

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6850. Min Act: -0.0000

Data Index: 1435142 (Python Code)

Max Activating Token Index: 263

Text #6

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6701. Min Act: -0.0000

Data Index: 1442836 (Python Code)

Max Activating Token Index: 139

Text #7

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6796. Min Act: -0.0000

Data Index: 1548142 (Python Code)

Max Activating Token Index: 292

Text #8

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6346. Min Act: -0.0000

Data Index: 1482832 (Python Code)

Max Activating Token Index: 133

Text #9

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6701. Min Act: -0.0000

Data Index: 1378155 (Python Code)

Max Activating Token Index: 425

Text #10

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6157. Min Act: -0.0000

Data Index: 1461759 (Python Code)

Max Activating Token Index: 248

Text #11

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6035. Min Act: -0.0000

Data Index: 1421151 (Python Code)

Max Activating Token Index: 296

Text #12

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6446. Min Act: -0.0000

Data Index: 1612993 (Python Code)

Max Activating Token Index: 640

Text #13

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.5424. Min Act: -0.0000

Data Index: 1401431 (Python Code)

Max Activating Token Index: 667

Text #14

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6606. Min Act: -0.0000

Data Index: 1399813 (Python Code)

Max Activating Token Index: 261

Text #15

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.5968. Min Act: -0.0000

Data Index: 1487519 (Python Code)

Max Activating Token Index: 951

Text #16

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.5745. Min Act: -0.0000

Data Index: 1613742 (Python Code)

Max Activating Token Index: 721

Text #17

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6492. Min Act: -0.0000

Data Index: 1636708 (Python Code)

Max Activating Token Index: 938

Text #18

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6434. Min Act: -0.0000

Data Index: 1645117 (Python Code)

Max Activating Token Index: 354

Text #19

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.5940. Min Act: -0.0000

Data Index: 1458517 (Python Code)

Max Activating Token Index: 227