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

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

Neuron 5127 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4929. Min Range: -2.4929

Max Act: 2.4929. Min Act: 0.0000

Data Index: 1513382 (Python Code)

Max Activating Token Index: 229

Text #1

Max Range: 2.4929. Min Range: -2.4929

Max Act: 2.3251. Min Act: 0.0000

Data Index: 1619130 (Python Code)

Max Activating Token Index: 287

Text #2

Max Range: 2.4929. Min Range: -2.4929

Max Act: 2.1771. Min Act: 0.0000

Data Index: 1505573 (Python Code)

Max Activating Token Index: 195

Text #3

Max Range: 2.4929. Min Range: -2.4929

Max Act: 2.1387. Min Act: -0.0000

Data Index: 1380121 (Python Code)

Max Activating Token Index: 1006

Text #4

Max Range: 2.4929. Min Range: -2.4929

Max Act: 2.0018. Min Act: -0.0000

Data Index: 1491457 (Python Code)

Max Activating Token Index: 65

Text #5

Max Range: 2.4929. Min Range: -2.4929

Max Act: 1.9575. Min Act: -0.0000

Data Index: 1528452 (Python Code)

Max Activating Token Index: 256

Text #6

Max Range: 2.4929. Min Range: -2.4929

Max Act: 1.9271. Min Act: 0.0000

Data Index: 1572588 (Python Code)

Max Activating Token Index: 240

Text #7

Max Range: 2.4929. Min Range: -2.4929

Max Act: 2.0327. Min Act: -0.0000

Data Index: 1438633 (Python Code)

Max Activating Token Index: 1018

Text #8

Max Range: 2.4929. Min Range: -2.4929

Max Act: 1.9088. Min Act: 0.0000

Data Index: 1596677 (Python Code)

Max Activating Token Index: 578

Text #9

Max Range: 2.4929. Min Range: -2.4929

Max Act: 1.9839. Min Act: 0.0000

Data Index: 1561641 (Python Code)

Max Activating Token Index: 289

Text #10

Max Range: 2.4929. Min Range: -2.4929

Max Act: 1.9942. Min Act: -0.0000

Data Index: 1583034 (Python Code)

Max Activating Token Index: 375

Text #11

Max Range: 2.4929. Min Range: -2.4929

Max Act: 1.8736. Min Act: -0.0000

Data Index: 1615536 (Python Code)

Max Activating Token Index: 154

Text #12

Max Range: 2.4929. Min Range: -2.4929

Max Act: 1.9739. Min Act: 0.0000

Data Index: 1632086 (Python Code)

Max Activating Token Index: 261

Text #13

Max Range: 2.4929. Min Range: -2.4929

Max Act: 1.9684. Min Act: -0.0000

Data Index: 1538482 (Python Code)

Max Activating Token Index: 987

Text #14

Max Range: 2.4929. Min Range: -2.4929

Max Act: 1.8627. Min Act: 0.0000

Data Index: 1608824 (Python Code)

Max Activating Token Index: 408

Text #15

Max Range: 2.4929. Min Range: -2.4929

Max Act: 2.0579. Min Act: 0.0000

Data Index: 1630228 (Python Code)

Max Activating Token Index: 149

Text #16

Max Range: 2.4929. Min Range: -2.4929

Max Act: 2.0492. Min Act: -0.0000

Data Index: 1511234 (Python Code)

Max Activating Token Index: 964

Text #17

Max Range: 2.4929. Min Range: -2.4929

Max Act: 1.9313. Min Act: 0.0000

Data Index: 1360722 (Python Code)

Max Activating Token Index: 89

Text #18

Max Range: 2.4929. Min Range: -2.4929

Max Act: 2.0373. Min Act: -0.0000

Data Index: 1580843 (Python Code)

Max Activating Token Index: 842

Text #19

Max Range: 2.4929. Min Range: -2.4929

Max Act: 1.8198. Min Act: 0.0000

Data Index: 1398547 (Python Code)

Max Activating Token Index: 657