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

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

Neuron 135 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: 1.5777. Min Range: -1.5777

Max Act: 1.5777. Min Act: -0.0000

Data Index: 1642234 (Python Code)

Max Activating Token Index: 853

Text #1

Max Range: 1.5777. Min Range: -1.5777

Max Act: 1.3760. Min Act: -0.0000

Data Index: 1597680 (Python Code)

Max Activating Token Index: 608

Text #2

Max Range: 1.5777. Min Range: -1.5777

Max Act: 1.2322. Min Act: -0.0000

Data Index: 1437169 (Python Code)

Max Activating Token Index: 953

Text #3

Max Range: 1.5777. Min Range: -1.5777

Max Act: 1.2648. Min Act: -0.0000

Data Index: 1580600 (Python Code)

Max Activating Token Index: 292

Text #4

Max Range: 1.5777. Min Range: -1.5777

Max Act: 1.1803. Min Act: -0.0000

Data Index: 1461667 (Python Code)

Max Activating Token Index: 989

Text #5

Max Range: 1.5777. Min Range: -1.5777

Max Act: 1.1420. Min Act: -0.0000

Data Index: 1377343 (Python Code)

Max Activating Token Index: 306

Text #6

Max Range: 1.5777. Min Range: -1.5777

Max Act: 1.1379. Min Act: 0.0000

Data Index: 1648004 (Python Code)

Max Activating Token Index: 911

Text #7

Max Range: 1.5777. Min Range: -1.5777

Max Act: 1.1864. Min Act: -0.0000

Data Index: 439769 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 1.5777. Min Range: -1.5777

Max Act: 1.2694. Min Act: 0.0000

Data Index: 1395582 (Python Code)

Max Activating Token Index: 469

Text #9

Max Range: 1.5777. Min Range: -1.5777

Max Act: 1.1391. Min Act: 0.0000

Data Index: 1568601 (Python Code)

Max Activating Token Index: 116

Text #10

Max Range: 1.5777. Min Range: -1.5777

Max Act: 1.0436. Min Act: -0.0000

Data Index: 1537584 (Python Code)

Max Activating Token Index: 237

Text #11

Max Range: 1.5777. Min Range: -1.5777

Max Act: 1.1052. Min Act: -0.0000

Data Index: 1508764 (Python Code)

Max Activating Token Index: 13

Text #12

Max Range: 1.5777. Min Range: -1.5777

Max Act: 1.1588. Min Act: -0.0000

Data Index: 1496385 (Python Code)

Max Activating Token Index: 793

Text #13

Max Range: 1.5777. Min Range: -1.5777

Max Act: 1.0764. Min Act: -0.0000

Data Index: 1375365 (Python Code)

Max Activating Token Index: 421

Text #14

Max Range: 1.5777. Min Range: -1.5777

Max Act: 1.1487. Min Act: -0.0000

Data Index: 714472 (C4 (Web Text))

Max Activating Token Index: 531

Text #15

Max Range: 1.5777. Min Range: -1.5777

Max Act: 1.0722. Min Act: 0.0000

Data Index: 1404379 (Python Code)

Max Activating Token Index: 580

Text #16

Max Range: 1.5777. Min Range: -1.5777

Max Act: 1.0664. Min Act: -0.0000

Data Index: 1419434 (Python Code)

Max Activating Token Index: 708

Text #17

Max Range: 1.5777. Min Range: -1.5777

Max Act: 0.9934. Min Act: -0.0000

Data Index: 963556 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 1.5777. Min Range: -1.5777

Max Act: 1.0156. Min Act: -0.0000

Data Index: 1189220 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 1.5777. Min Range: -1.5777

Max Act: 0.9637. Min Act: -0.0000

Data Index: 1423202 (Python Code)

Max Activating Token Index: 496