Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1475 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.1778. Min Range: -3.1778

Max Act: 3.1376. Min Act: -0.0000

Data Index: 1632604 (Python Code)

Max Activating Token Index: 374

Text #1

Max Range: 3.1778. Min Range: -3.1778

Max Act: 3.1778. Min Act: -0.0000

Data Index: 1531160 (Python Code)

Max Activating Token Index: 570

Text #2

Max Range: 3.1778. Min Range: -3.1778

Max Act: 2.7677. Min Act: -0.0000

Data Index: 1566428 (Python Code)

Max Activating Token Index: 161

Text #3

Max Range: 3.1778. Min Range: -3.1778

Max Act: 2.9022. Min Act: -0.0000

Data Index: 1581043 (Python Code)

Max Activating Token Index: 300

Text #4

Max Range: 3.1778. Min Range: -3.1778

Max Act: 2.5297. Min Act: -0.0001

Data Index: 1646578 (Python Code)

Max Activating Token Index: 290

Text #5

Max Range: 3.1778. Min Range: -3.1778

Max Act: 2.8602. Min Act: -0.0000

Data Index: 1418033 (Python Code)

Max Activating Token Index: 859

Text #6

Max Range: 3.1778. Min Range: -3.1778

Max Act: 2.6029. Min Act: -0.0000

Data Index: 1500735 (Python Code)

Max Activating Token Index: 135

Text #7

Max Range: 3.1778. Min Range: -3.1778

Max Act: 2.7948. Min Act: -0.0000

Data Index: 1480306 (Python Code)

Max Activating Token Index: 1011

Text #8

Max Range: 3.1778. Min Range: -3.1778

Max Act: 2.6297. Min Act: -0.0000

Data Index: 1416811 (Python Code)

Max Activating Token Index: 162

Text #9

Max Range: 3.1778. Min Range: -3.1778

Max Act: 2.6240. Min Act: -0.0001

Data Index: 1532807 (Python Code)

Max Activating Token Index: 693

Text #10

Max Range: 3.1778. Min Range: -3.1778

Max Act: 2.5734. Min Act: -0.0001

Data Index: 1474852 (Python Code)

Max Activating Token Index: 387

Text #11

Max Range: 3.1778. Min Range: -3.1778

Max Act: 2.5576. Min Act: -0.0001

Data Index: 1414955 (Python Code)

Max Activating Token Index: 170

Text #12

Max Range: 3.1778. Min Range: -3.1778

Max Act: 2.5571. Min Act: -0.0001

Data Index: 1571836 (Python Code)

Max Activating Token Index: 921

Text #13

Max Range: 3.1778. Min Range: -3.1778

Max Act: 2.6896. Min Act: -0.0001

Data Index: 1522768 (Python Code)

Max Activating Token Index: 427

Text #14

Max Range: 3.1778. Min Range: -3.1778

Max Act: 2.5469. Min Act: -0.0000

Data Index: 1628276 (Python Code)

Max Activating Token Index: 932

Text #15

Max Range: 3.1778. Min Range: -3.1778

Max Act: 2.6760. Min Act: -0.0000

Data Index: 1590914 (Python Code)

Max Activating Token Index: 213

Text #16

Max Range: 3.1778. Min Range: -3.1778

Max Act: 2.3777. Min Act: -0.0000

Data Index: 1583640 (Python Code)

Max Activating Token Index: 209

Text #17

Max Range: 3.1778. Min Range: -3.1778

Max Act: 2.4930. Min Act: -0.0001

Data Index: 1488855 (Python Code)

Max Activating Token Index: 286

Text #18

Max Range: 3.1778. Min Range: -3.1778

Max Act: 2.6088. Min Act: -0.0000

Data Index: 1456420 (Python Code)

Max Activating Token Index: 241

Text #19

Max Range: 3.1778. Min Range: -3.1778

Max Act: 2.6028. Min Act: -0.0001

Data Index: 1391042 (Python Code)

Max Activating Token Index: 328