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

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

Neuron 1568 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: 0.4789. Min Range: -0.4789

Max Act: 0.4789. Min Act: -0.0000

Data Index: 1386559 (Python Code)

Max Activating Token Index: 789

Text #1

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3475. Min Act: -0.0000

Data Index: 1535810 (Python Code)

Max Activating Token Index: 788

Text #2

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3510. Min Act: -0.0000

Data Index: 1546413 (Python Code)

Max Activating Token Index: 322

Text #3

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3436. Min Act: -0.0000

Data Index: 1648515 (Python Code)

Max Activating Token Index: 618

Text #4

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3314. Min Act: -0.0000

Data Index: 1096920 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3015. Min Act: -0.0000

Data Index: 657231 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3101. Min Act: -0.0000

Data Index: 1433560 (Python Code)

Max Activating Token Index: 537

Text #7

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.2863. Min Act: -0.0000

Data Index: 314921 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3046. Min Act: -0.0000

Data Index: 1489400 (Python Code)

Max Activating Token Index: 636

Text #9

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.2843. Min Act: -0.0000

Data Index: 374089 (C4 (Web Text))

Max Activating Token Index: 777

Text #10

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.2979. Min Act: -0.0000

Data Index: 469078 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.2744. Min Act: -0.0000

Data Index: 528453 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.2840. Min Act: -0.0000

Data Index: 1533325 (Python Code)

Max Activating Token Index: 731

Text #13

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.2825. Min Act: -0.0000

Data Index: 32087 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.2970. Min Act: -0.0000

Data Index: 1506401 (Python Code)

Max Activating Token Index: 828

Text #15

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.2891. Min Act: -0.0000

Data Index: 1485598 (Python Code)

Max Activating Token Index: 317

Text #16

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.2755. Min Act: -0.0000

Data Index: 1483131 (Python Code)

Max Activating Token Index: 332

Text #17

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.2851. Min Act: -0.0000

Data Index: 971972 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.2814. Min Act: -0.0000

Data Index: 1467163 (Python Code)

Max Activating Token Index: 511

Text #19

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.2693. Min Act: -0.0000

Data Index: 1485270 (Python Code)

Max Activating Token Index: 664