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

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

Neuron 5899 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: 1.3643. Min Range: -1.3643

Max Act: 1.3643. Min Act: -0.0000

Data Index: 1518396 (Python Code)

Max Activating Token Index: 614

Text #1

Max Range: 1.3643. Min Range: -1.3643

Max Act: 1.3175. Min Act: -0.0000

Data Index: 1494199 (Python Code)

Max Activating Token Index: 50

Text #2

Max Range: 1.3643. Min Range: -1.3643

Max Act: 1.3109. Min Act: -0.0000

Data Index: 1260706 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 1.3643. Min Range: -1.3643

Max Act: 1.2962. Min Act: -0.0000

Data Index: 1491006 (Python Code)

Max Activating Token Index: 130

Text #4

Max Range: 1.3643. Min Range: -1.3643

Max Act: 1.2693. Min Act: -0.0000

Data Index: 1557628 (Python Code)

Max Activating Token Index: 176

Text #5

Max Range: 1.3643. Min Range: -1.3643

Max Act: 1.2574. Min Act: -0.0000

Data Index: 675782 (C4 (Web Text))

Max Activating Token Index: 553

Text #6

Max Range: 1.3643. Min Range: -1.3643

Max Act: 1.1256. Min Act: -0.0000

Data Index: 1497594 (Python Code)

Max Activating Token Index: 214

Text #7

Max Range: 1.3643. Min Range: -1.3643

Max Act: 1.2100. Min Act: -0.0000

Data Index: 1398919 (Python Code)

Max Activating Token Index: 473

Text #8

Max Range: 1.3643. Min Range: -1.3643

Max Act: 1.1560. Min Act: -0.0000

Data Index: 1366238 (Python Code)

Max Activating Token Index: 443

Text #9

Max Range: 1.3643. Min Range: -1.3643

Max Act: 1.2200. Min Act: -0.0000

Data Index: 1334591 (C4 (Web Text))

Max Activating Token Index: 212

Text #10

Max Range: 1.3643. Min Range: -1.3643

Max Act: 1.1208. Min Act: -0.0000

Data Index: 687523 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 1.3643. Min Range: -1.3643

Max Act: 1.1812. Min Act: -0.0000

Data Index: 1560089 (Python Code)

Max Activating Token Index: 174

Text #12

Max Range: 1.3643. Min Range: -1.3643

Max Act: 1.1782. Min Act: -0.0000

Data Index: 1533155 (Python Code)

Max Activating Token Index: 531

Text #13

Max Range: 1.3643. Min Range: -1.3643

Max Act: 1.0462. Min Act: -0.0000

Data Index: 134763 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 1.3643. Min Range: -1.3643

Max Act: 1.0991. Min Act: -0.0000

Data Index: 1496959 (Python Code)

Max Activating Token Index: 425

Text #15

Max Range: 1.3643. Min Range: -1.3643

Max Act: 1.0946. Min Act: -0.0000

Data Index: 1490475 (Python Code)

Max Activating Token Index: 574

Text #16

Max Range: 1.3643. Min Range: -1.3643

Max Act: 1.1586. Min Act: -0.0000

Data Index: 153440 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 1.3643. Min Range: -1.3643

Max Act: 1.0810. Min Act: -0.0000

Data Index: 1472644 (Python Code)

Max Activating Token Index: 697

Text #18

Max Range: 1.3643. Min Range: -1.3643

Max Act: 0.9984. Min Act: -0.0000

Data Index: 1360904 (Python Code)

Max Activating Token Index: 865

Text #19

Max Range: 1.3643. Min Range: -1.3643

Max Act: 0.9900. Min Act: -0.0000

Data Index: 1127181 (C4 (Web Text))

Max Activating Token Index: 930