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

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

Neuron 4338 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0732. Min Range: -3.0732

Max Act: 3.0732. Min Act: -0.0000

Data Index: 1513044 (Python Code)

Max Activating Token Index: 98

Text #1

Max Range: 3.0732. Min Range: -3.0732

Max Act: 2.5191. Min Act: -0.0000

Data Index: 1524730 (Python Code)

Max Activating Token Index: 904

Text #2

Max Range: 3.0732. Min Range: -3.0732

Max Act: 2.4611. Min Act: -0.0000

Data Index: 1391509 (Python Code)

Max Activating Token Index: 314

Text #3

Max Range: 3.0732. Min Range: -3.0732

Max Act: 2.2750. Min Act: -0.0000

Data Index: 1371499 (Python Code)

Max Activating Token Index: 114

Text #4

Max Range: 3.0732. Min Range: -3.0732

Max Act: 2.0560. Min Act: -0.0000

Data Index: 1466161 (Python Code)

Max Activating Token Index: 359

Text #5

Max Range: 3.0732. Min Range: -3.0732

Max Act: 2.1379. Min Act: -0.0000

Data Index: 1498193 (Python Code)

Max Activating Token Index: 762

Text #6

Max Range: 3.0732. Min Range: -3.0732

Max Act: 2.0287. Min Act: -0.0000

Data Index: 1430694 (Python Code)

Max Activating Token Index: 462

Text #7

Max Range: 3.0732. Min Range: -3.0732

Max Act: 2.0987. Min Act: -0.0000

Data Index: 1581890 (Python Code)

Max Activating Token Index: 858

Text #8

Max Range: 3.0732. Min Range: -3.0732

Max Act: 2.1120. Min Act: -0.0000

Data Index: 1380025 (Python Code)

Max Activating Token Index: 634

Text #9

Max Range: 3.0732. Min Range: -3.0732

Max Act: 2.0597. Min Act: -0.0000

Data Index: 1455133 (Python Code)

Max Activating Token Index: 532

Text #10

Max Range: 3.0732. Min Range: -3.0732

Max Act: 1.9368. Min Act: -0.0000

Data Index: 1399741 (Python Code)

Max Activating Token Index: 868

Text #11

Max Range: 3.0732. Min Range: -3.0732

Max Act: 1.9932. Min Act: -0.0000

Data Index: 1528046 (Python Code)

Max Activating Token Index: 705

Text #12

Max Range: 3.0732. Min Range: -3.0732

Max Act: 2.2331. Min Act: -0.0000

Data Index: 1563460 (Python Code)

Max Activating Token Index: 737

Text #13

Max Range: 3.0732. Min Range: -3.0732

Max Act: 1.8532. Min Act: -0.0000

Data Index: 1576733 (Python Code)

Max Activating Token Index: 832

Text #14

Max Range: 3.0732. Min Range: -3.0732

Max Act: 1.9663. Min Act: -0.0000

Data Index: 1439527 (Python Code)

Max Activating Token Index: 701

Text #15

Max Range: 3.0732. Min Range: -3.0732

Max Act: 1.9556. Min Act: -0.0000

Data Index: 1624302 (Python Code)

Max Activating Token Index: 631

Text #16

Max Range: 3.0732. Min Range: -3.0732

Max Act: 1.8743. Min Act: -0.0000

Data Index: 1423457 (Python Code)

Max Activating Token Index: 872

Text #17

Max Range: 3.0732. Min Range: -3.0732

Max Act: 2.0549. Min Act: -0.0000

Data Index: 1620839 (Python Code)

Max Activating Token Index: 249

Text #18

Max Range: 3.0732. Min Range: -3.0732

Max Act: 2.0006. Min Act: -0.0000

Data Index: 1617778 (Python Code)

Max Activating Token Index: 713

Text #19

Max Range: 3.0732. Min Range: -3.0732

Max Act: 1.8875. Min Act: -0.0000

Data Index: 1520427 (Python Code)

Max Activating Token Index: 468