Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4185 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3437. Min Range: -1.3437

Max Act: 1.3437. Min Act: -0.0000

Data Index: 1598160 (Python Code)

Max Activating Token Index: 963

Text #1

Max Range: 1.3437. Min Range: -1.3437

Max Act: 1.1975. Min Act: -0.0000

Data Index: 1330902 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 1.3437. Min Range: -1.3437

Max Act: 1.1105. Min Act: -0.0000

Data Index: 1434463 (Python Code)

Max Activating Token Index: 227

Text #3

Max Range: 1.3437. Min Range: -1.3437

Max Act: 1.0739. Min Act: -0.0000

Data Index: 1447467 (Python Code)

Max Activating Token Index: 718

Text #4

Max Range: 1.3437. Min Range: -1.3437

Max Act: 1.0705. Min Act: -0.0000

Data Index: 1615864 (Python Code)

Max Activating Token Index: 1010

Text #5

Max Range: 1.3437. Min Range: -1.3437

Max Act: 1.0494. Min Act: -0.0000

Data Index: 1563570 (Python Code)

Max Activating Token Index: 364

Text #6

Max Range: 1.3437. Min Range: -1.3437

Max Act: 0.9981. Min Act: -0.0000

Data Index: 1529372 (Python Code)

Max Activating Token Index: 804

Text #7

Max Range: 1.3437. Min Range: -1.3437

Max Act: 0.9812. Min Act: -0.0000

Data Index: 1413956 (Python Code)

Max Activating Token Index: 851

Text #8

Max Range: 1.3437. Min Range: -1.3437

Max Act: 0.9557. Min Act: -0.0000

Data Index: 1589410 (Python Code)

Max Activating Token Index: 323

Text #9

Max Range: 1.3437. Min Range: -1.3437

Max Act: 0.9440. Min Act: -0.0000

Data Index: 1530126 (Python Code)

Max Activating Token Index: 754

Text #10

Max Range: 1.3437. Min Range: -1.3437

Max Act: 1.0169. Min Act: -0.0000

Data Index: 1588275 (Python Code)

Max Activating Token Index: 287

Text #11

Max Range: 1.3437. Min Range: -1.3437

Max Act: 0.9317. Min Act: -0.0000

Data Index: 1311930 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 1.3437. Min Range: -1.3437

Max Act: 0.9780. Min Act: -0.0000

Data Index: 1417531 (Python Code)

Max Activating Token Index: 516

Text #13

Max Range: 1.3437. Min Range: -1.3437

Max Act: 0.9473. Min Act: -0.0000

Data Index: 1570797 (Python Code)

Max Activating Token Index: 996

Text #14

Max Range: 1.3437. Min Range: -1.3437

Max Act: 0.9288. Min Act: -0.0000

Data Index: 1621210 (Python Code)

Max Activating Token Index: 122

Text #15

Max Range: 1.3437. Min Range: -1.3437

Max Act: 0.9715. Min Act: -0.0000

Data Index: 1479085 (Python Code)

Max Activating Token Index: 120

Text #16

Max Range: 1.3437. Min Range: -1.3437

Max Act: 0.9138. Min Act: -0.0000

Data Index: 1484271 (Python Code)

Max Activating Token Index: 598

Text #17

Max Range: 1.3437. Min Range: -1.3437

Max Act: 0.8559. Min Act: -0.0000

Data Index: 1644448 (Python Code)

Max Activating Token Index: 74

Text #18

Max Range: 1.3437. Min Range: -1.3437

Max Act: 0.8287. Min Act: -0.0000

Data Index: 1592993 (Python Code)

Max Activating Token Index: 69

Text #19

Max Range: 1.3437. Min Range: -1.3437

Max Act: 0.9076. Min Act: -0.0000

Data Index: 1474504 (Python Code)

Max Activating Token Index: 550