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

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

Neuron 5032 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2801. Min Range: -1.2801

Max Act: 1.2801. Min Act: -0.0000

Data Index: 1530727 (Python Code)

Max Activating Token Index: 78

Text #1

Max Range: 1.2801. Min Range: -1.2801

Max Act: 1.2318. Min Act: -0.0000

Data Index: 1501695 (Python Code)

Max Activating Token Index: 883

Text #2

Max Range: 1.2801. Min Range: -1.2801

Max Act: 1.2002. Min Act: 0.0000

Data Index: 1445120 (Python Code)

Max Activating Token Index: 278

Text #3

Max Range: 1.2801. Min Range: -1.2801

Max Act: 1.1734. Min Act: -0.0000

Data Index: 1650029 (Python Code)

Max Activating Token Index: 605

Text #4

Max Range: 1.2801. Min Range: -1.2801

Max Act: 1.1132. Min Act: -0.0000

Data Index: 1428426 (Python Code)

Max Activating Token Index: 91

Text #5

Max Range: 1.2801. Min Range: -1.2801

Max Act: 1.1425. Min Act: 0.0001

Data Index: 1586757 (Python Code)

Max Activating Token Index: 663

Text #6

Max Range: 1.2801. Min Range: -1.2801

Max Act: 1.1046. Min Act: 0.0001

Data Index: 1626192 (Python Code)

Max Activating Token Index: 307

Text #7

Max Range: 1.2801. Min Range: -1.2801

Max Act: 1.0997. Min Act: -0.0000

Data Index: 1421387 (Python Code)

Max Activating Token Index: 366

Text #8

Max Range: 1.2801. Min Range: -1.2801

Max Act: 1.1143. Min Act: -0.0000

Data Index: 1513723 (Python Code)

Max Activating Token Index: 141

Text #9

Max Range: 1.2801. Min Range: -1.2801

Max Act: 1.0011. Min Act: 0.0000

Data Index: 1640985 (Python Code)

Max Activating Token Index: 646

Text #10

Max Range: 1.2801. Min Range: -1.2801

Max Act: 0.9741. Min Act: 0.0000

Data Index: 1524739 (Python Code)

Max Activating Token Index: 633

Text #11

Max Range: 1.2801. Min Range: -1.2801

Max Act: 1.0275. Min Act: 0.0000

Data Index: 1540984 (Python Code)

Max Activating Token Index: 441

Text #12

Max Range: 1.2801. Min Range: -1.2801

Max Act: 1.0015. Min Act: -0.0000

Data Index: 1648376 (Python Code)

Max Activating Token Index: 708

Text #13

Max Range: 1.2801. Min Range: -1.2801

Max Act: 0.9665. Min Act: -0.0000

Data Index: 1484002 (Python Code)

Max Activating Token Index: 67

Text #14

Max Range: 1.2801. Min Range: -1.2801

Max Act: 0.9369. Min Act: -0.0000

Data Index: 1404070 (Python Code)

Max Activating Token Index: 948

Text #15

Max Range: 1.2801. Min Range: -1.2801

Max Act: 0.9398. Min Act: 0.0000

Data Index: 1596315 (Python Code)

Max Activating Token Index: 58

Text #16

Max Range: 1.2801. Min Range: -1.2801

Max Act: 0.9369. Min Act: 0.0000

Data Index: 1656724 (Python Code)

Max Activating Token Index: 710

Text #17

Max Range: 1.2801. Min Range: -1.2801

Max Act: 0.9071. Min Act: 0.0000

Data Index: 1594617 (Python Code)

Max Activating Token Index: 230

Text #18

Max Range: 1.2801. Min Range: -1.2801

Max Act: 0.9627. Min Act: -0.0000

Data Index: 1511977 (Python Code)

Max Activating Token Index: 597

Text #19

Max Range: 1.2801. Min Range: -1.2801

Max Act: 0.8996. Min Act: 0.0000

Data Index: 1575693 (Python Code)

Max Activating Token Index: 317