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

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

Neuron 3038 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9698. Min Range: -2.9698

Max Act: 2.9698. Min Act: -0.0000

Data Index: 1423960 (Python Code)

Max Activating Token Index: 604

Text #1

Max Range: 2.9698. Min Range: -2.9698

Max Act: 2.6373. Min Act: -0.0000

Data Index: 1592187 (Python Code)

Max Activating Token Index: 277

Text #2

Max Range: 2.9698. Min Range: -2.9698

Max Act: 2.4965. Min Act: -0.0000

Data Index: 1366108 (Python Code)

Max Activating Token Index: 552

Text #3

Max Range: 2.9698. Min Range: -2.9698

Max Act: 2.2795. Min Act: -0.0000

Data Index: 1394210 (Python Code)

Max Activating Token Index: 693

Text #4

Max Range: 2.9698. Min Range: -2.9698

Max Act: 2.1763. Min Act: -0.0000

Data Index: 1379577 (Python Code)

Max Activating Token Index: 865

Text #5

Max Range: 2.9698. Min Range: -2.9698

Max Act: 2.3438. Min Act: -0.0000

Data Index: 1405956 (Python Code)

Max Activating Token Index: 112

Text #6

Max Range: 2.9698. Min Range: -2.9698

Max Act: 2.1555. Min Act: -0.0000

Data Index: 1380734 (Python Code)

Max Activating Token Index: 954

Text #7

Max Range: 2.9698. Min Range: -2.9698

Max Act: 2.1815. Min Act: -0.0000

Data Index: 1454732 (Python Code)

Max Activating Token Index: 34

Text #8

Max Range: 2.9698. Min Range: -2.9698

Max Act: 2.1555. Min Act: -0.0000

Data Index: 1536167 (Python Code)

Max Activating Token Index: 434

Text #9

Max Range: 2.9698. Min Range: -2.9698

Max Act: 2.0769. Min Act: -0.0000

Data Index: 1500035 (Python Code)

Max Activating Token Index: 783

Text #10

Max Range: 2.9698. Min Range: -2.9698

Max Act: 2.0813. Min Act: -0.0000

Data Index: 1549331 (Python Code)

Max Activating Token Index: 331

Text #11

Max Range: 2.9698. Min Range: -2.9698

Max Act: 2.0039. Min Act: -0.0000

Data Index: 1508390 (Python Code)

Max Activating Token Index: 568

Text #12

Max Range: 2.9698. Min Range: -2.9698

Max Act: 2.0977. Min Act: -0.0000

Data Index: 1426420 (Python Code)

Max Activating Token Index: 225

Text #13

Max Range: 2.9698. Min Range: -2.9698

Max Act: 1.9448. Min Act: -0.0000

Data Index: 1549195 (Python Code)

Max Activating Token Index: 237

Text #14

Max Range: 2.9698. Min Range: -2.9698

Max Act: 1.9507. Min Act: -0.0000

Data Index: 1503184 (Python Code)

Max Activating Token Index: 938

Text #15

Max Range: 2.9698. Min Range: -2.9698

Max Act: 1.9057. Min Act: -0.0000

Data Index: 1414061 (Python Code)

Max Activating Token Index: 837

Text #16

Max Range: 2.9698. Min Range: -2.9698

Max Act: 1.8984. Min Act: -0.0000

Data Index: 1635762 (Python Code)

Max Activating Token Index: 139

Text #17

Max Range: 2.9698. Min Range: -2.9698

Max Act: 1.8828. Min Act: -0.0000

Data Index: 1363349 (Python Code)

Max Activating Token Index: 421

Text #18

Max Range: 2.9698. Min Range: -2.9698

Max Act: 1.9137. Min Act: -0.0000

Data Index: 1412981 (Python Code)

Max Activating Token Index: 442

Text #19

Max Range: 2.9698. Min Range: -2.9698

Max Act: 1.9040. Min Act: -0.0000

Data Index: 1520307 (Python Code)

Max Activating Token Index: 448