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

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

Neuron 251 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: 1.8821. Min Range: -1.8821

Max Act: 1.8821. Min Act: 0.0000

Data Index: 531006 (C4 (Web Text))

Max Activating Token Index: 206

Text #1

Max Range: 1.8821. Min Range: -1.8821

Max Act: 1.6640. Min Act: -0.0000

Data Index: 1489342 (Python Code)

Max Activating Token Index: 759

Text #2

Max Range: 1.8821. Min Range: -1.8821

Max Act: 1.5772. Min Act: -0.0000

Data Index: 1420252 (Python Code)

Max Activating Token Index: 330

Text #3

Max Range: 1.8821. Min Range: -1.8821

Max Act: 1.4451. Min Act: -0.0000

Data Index: 1614719 (Python Code)

Max Activating Token Index: 181

Text #4

Max Range: 1.8821. Min Range: -1.8821

Max Act: 1.4822. Min Act: -0.0000

Data Index: 1467159 (Python Code)

Max Activating Token Index: 658

Text #5

Max Range: 1.8821. Min Range: -1.8821

Max Act: 1.4643. Min Act: -0.0000

Data Index: 1379460 (Python Code)

Max Activating Token Index: 845

Text #6

Max Range: 1.8821. Min Range: -1.8821

Max Act: 1.3747. Min Act: -0.0000

Data Index: 1589692 (Python Code)

Max Activating Token Index: 849

Text #7

Max Range: 1.8821. Min Range: -1.8821

Max Act: 1.3328. Min Act: -0.0000

Data Index: 1535664 (Python Code)

Max Activating Token Index: 710

Text #8

Max Range: 1.8821. Min Range: -1.8821

Max Act: 1.2380. Min Act: -0.0000

Data Index: 1470235 (Python Code)

Max Activating Token Index: 552

Text #9

Max Range: 1.8821. Min Range: -1.8821

Max Act: 1.2633. Min Act: -0.0000

Data Index: 1399961 (Python Code)

Max Activating Token Index: 914

Text #10

Max Range: 1.8821. Min Range: -1.8821

Max Act: 1.2267. Min Act: -0.0000

Data Index: 1488327 (Python Code)

Max Activating Token Index: 555

Text #11

Max Range: 1.8821. Min Range: -1.8821

Max Act: 1.2858. Min Act: -0.0000

Data Index: 1469808 (Python Code)

Max Activating Token Index: 579

Text #12

Max Range: 1.8821. Min Range: -1.8821

Max Act: 1.2096. Min Act: -0.0000

Data Index: 1570083 (Python Code)

Max Activating Token Index: 135

Text #13

Max Range: 1.8821. Min Range: -1.8821

Max Act: 1.0627. Min Act: -0.0000

Data Index: 1461872 (Python Code)

Max Activating Token Index: 216

Text #14

Max Range: 1.8821. Min Range: -1.8821

Max Act: 1.1434. Min Act: -0.0000

Data Index: 1289113 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 1.8821. Min Range: -1.8821

Max Act: 1.2597. Min Act: -0.0000

Data Index: 1656543 (Python Code)

Max Activating Token Index: 220

Text #16

Max Range: 1.8821. Min Range: -1.8821

Max Act: 1.0902. Min Act: -0.0000

Data Index: 1369661 (Python Code)

Max Activating Token Index: 678

Text #17

Max Range: 1.8821. Min Range: -1.8821

Max Act: 1.1866. Min Act: -0.0000

Data Index: 1489457 (Python Code)

Max Activating Token Index: 649

Text #18

Max Range: 1.8821. Min Range: -1.8821

Max Act: 1.1395. Min Act: -0.0000

Data Index: 1644222 (Python Code)

Max Activating Token Index: 732

Text #19

Max Range: 1.8821. Min Range: -1.8821

Max Act: 1.1419. Min Act: 0.0000

Data Index: 1431206 (Python Code)

Max Activating Token Index: 567