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

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

Neuron 4923 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: 1.5474. Min Range: -1.5474

Max Act: 1.5248. Min Act: -0.0000

Data Index: 1523595 (Python Code)

Max Activating Token Index: 517

Text #1

Max Range: 1.5474. Min Range: -1.5474

Max Act: 1.5474. Min Act: -0.0000

Data Index: 1440970 (Python Code)

Max Activating Token Index: 284

Text #2

Max Range: 1.5474. Min Range: -1.5474

Max Act: 1.4227. Min Act: -0.0000

Data Index: 1438222 (Python Code)

Max Activating Token Index: 224

Text #3

Max Range: 1.5474. Min Range: -1.5474

Max Act: 1.3809. Min Act: -0.0000

Data Index: 1638075 (Python Code)

Max Activating Token Index: 382

Text #4

Max Range: 1.5474. Min Range: -1.5474

Max Act: 1.3843. Min Act: -0.0000

Data Index: 1520301 (Python Code)

Max Activating Token Index: 805

Text #5

Max Range: 1.5474. Min Range: -1.5474

Max Act: 1.4682. Min Act: -0.0000

Data Index: 1565679 (Python Code)

Max Activating Token Index: 136

Text #6

Max Range: 1.5474. Min Range: -1.5474

Max Act: 1.2839. Min Act: -0.0000

Data Index: 1424047 (Python Code)

Max Activating Token Index: 619

Text #7

Max Range: 1.5474. Min Range: -1.5474

Max Act: 1.2944. Min Act: -0.0000

Data Index: 1408811 (Python Code)

Max Activating Token Index: 667

Text #8

Max Range: 1.5474. Min Range: -1.5474

Max Act: 1.3449. Min Act: -0.0000

Data Index: 702284 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 1.5474. Min Range: -1.5474

Max Act: 1.2524. Min Act: -0.0000

Data Index: 1386643 (Python Code)

Max Activating Token Index: 180

Text #10

Max Range: 1.5474. Min Range: -1.5474

Max Act: 1.4010. Min Act: -0.0000

Data Index: 425855 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 1.5474. Min Range: -1.5474

Max Act: 1.2357. Min Act: -0.0000

Data Index: 1410611 (Python Code)

Max Activating Token Index: 812

Text #12

Max Range: 1.5474. Min Range: -1.5474

Max Act: 1.2218. Min Act: -0.0000

Data Index: 635831 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 1.5474. Min Range: -1.5474

Max Act: 1.2756. Min Act: -0.0000

Data Index: 1384580 (Python Code)

Max Activating Token Index: 704

Text #14

Max Range: 1.5474. Min Range: -1.5474

Max Act: 1.2642. Min Act: -0.0000

Data Index: 1649254 (Python Code)

Max Activating Token Index: 280

Text #15

Max Range: 1.5474. Min Range: -1.5474

Max Act: 1.1878. Min Act: -0.0000

Data Index: 666818 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 1.5474. Min Range: -1.5474

Max Act: 1.2883. Min Act: -0.0000

Data Index: 534918 (C4 (Web Text))

Max Activating Token Index: 587

Text #17

Max Range: 1.5474. Min Range: -1.5474

Max Act: 1.2064. Min Act: -0.0000

Data Index: 1461310 (Python Code)

Max Activating Token Index: 223

Text #18

Max Range: 1.5474. Min Range: -1.5474

Max Act: 1.2193. Min Act: -0.0000

Data Index: 1472356 (Python Code)

Max Activating Token Index: 629

Text #19

Max Range: 1.5474. Min Range: -1.5474

Max Act: 1.3632. Min Act: -0.0000

Data Index: 1570271 (Python Code)

Max Activating Token Index: 835