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

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

Neuron 3673 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.0043. Min Range: -4.0043

Max Act: 3.7699. Min Act: -0.0000

Data Index: 1601182 (Python Code)

Max Activating Token Index: 283

Text #1

Max Range: 4.0043. Min Range: -4.0043

Max Act: 3.8918. Min Act: -0.0000

Data Index: 1609097 (Python Code)

Max Activating Token Index: 19

Text #2

Max Range: 4.0043. Min Range: -4.0043

Max Act: 3.6233. Min Act: -0.0000

Data Index: 1509751 (Python Code)

Max Activating Token Index: 160

Text #3

Max Range: 4.0043. Min Range: -4.0043

Max Act: 3.7648. Min Act: -0.0000

Data Index: 1512386 (Python Code)

Max Activating Token Index: 372

Text #4

Max Range: 4.0043. Min Range: -4.0043

Max Act: 3.5938. Min Act: -0.0000

Data Index: 1366098 (Python Code)

Max Activating Token Index: 275

Text #5

Max Range: 4.0043. Min Range: -4.0043

Max Act: 3.4397. Min Act: -0.0000

Data Index: 1372613 (Python Code)

Max Activating Token Index: 113

Text #6

Max Range: 4.0043. Min Range: -4.0043

Max Act: 3.1191. Min Act: -0.0000

Data Index: 1624569 (Python Code)

Max Activating Token Index: 962

Text #7

Max Range: 4.0043. Min Range: -4.0043

Max Act: 2.9284. Min Act: -0.0000

Data Index: 1405810 (Python Code)

Max Activating Token Index: 356

Text #8

Max Range: 4.0043. Min Range: -4.0043

Max Act: 3.2686. Min Act: -0.0000

Data Index: 1525142 (Python Code)

Max Activating Token Index: 550

Text #9

Max Range: 4.0043. Min Range: -4.0043

Max Act: 3.1004. Min Act: -0.0000

Data Index: 1555831 (Python Code)

Max Activating Token Index: 558

Text #10

Max Range: 4.0043. Min Range: -4.0043

Max Act: 3.3914. Min Act: -0.0000

Data Index: 1533973 (Python Code)

Max Activating Token Index: 755

Text #11

Max Range: 4.0043. Min Range: -4.0043

Max Act: 4.0043. Min Act: -0.0000

Data Index: 1567795 (Python Code)

Max Activating Token Index: 864

Text #12

Max Range: 4.0043. Min Range: -4.0043

Max Act: 2.8690. Min Act: -0.0000

Data Index: 1521953 (Python Code)

Max Activating Token Index: 660

Text #13

Max Range: 4.0043. Min Range: -4.0043

Max Act: 2.9082. Min Act: -0.0000

Data Index: 1387205 (Python Code)

Max Activating Token Index: 397

Text #14

Max Range: 4.0043. Min Range: -4.0043

Max Act: 2.6711. Min Act: -0.0000

Data Index: 1565955 (Python Code)

Max Activating Token Index: 971

Text #15

Max Range: 4.0043. Min Range: -4.0043

Max Act: 2.7811. Min Act: -0.0000

Data Index: 1578652 (Python Code)

Max Activating Token Index: 797

Text #16

Max Range: 4.0043. Min Range: -4.0043

Max Act: 2.4962. Min Act: -0.0000

Data Index: 1510493 (Python Code)

Max Activating Token Index: 459

Text #17

Max Range: 4.0043. Min Range: -4.0043

Max Act: 2.7367. Min Act: -0.0000

Data Index: 1517354 (Python Code)

Max Activating Token Index: 273

Text #18

Max Range: 4.0043. Min Range: -4.0043

Max Act: 2.7346. Min Act: -0.0000

Data Index: 1432641 (Python Code)

Max Activating Token Index: 342

Text #19

Max Range: 4.0043. Min Range: -4.0043

Max Act: 2.7049. Min Act: -0.0000

Data Index: 1369732 (Python Code)

Max Activating Token Index: 523