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

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

Neuron 3008 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1693. Min Range: -3.1693

Max Act: 3.0037. Min Act: -0.0000

Data Index: 1517140 (Python Code)

Max Activating Token Index: 769

Text #1

Max Range: 3.1693. Min Range: -3.1693

Max Act: 3.1693. Min Act: -0.0000

Data Index: 976095 (C4 (Web Text))

Max Activating Token Index: 592

Text #2

Max Range: 3.1693. Min Range: -3.1693

Max Act: 2.6610. Min Act: -0.0000

Data Index: 1539976 (Python Code)

Max Activating Token Index: 288

Text #3

Max Range: 3.1693. Min Range: -3.1693

Max Act: 2.5435. Min Act: -0.0000

Data Index: 1524730 (Python Code)

Max Activating Token Index: 322

Text #4

Max Range: 3.1693. Min Range: -3.1693

Max Act: 2.6525. Min Act: -0.0000

Data Index: 992319 (C4 (Web Text))

Max Activating Token Index: 1008

Text #5

Max Range: 3.1693. Min Range: -3.1693

Max Act: 2.7599. Min Act: -0.0000

Data Index: 1511952 (Python Code)

Max Activating Token Index: 194

Text #6

Max Range: 3.1693. Min Range: -3.1693

Max Act: 2.6839. Min Act: -0.0000

Data Index: 1411287 (Python Code)

Max Activating Token Index: 713

Text #7

Max Range: 3.1693. Min Range: -3.1693

Max Act: 2.3882. Min Act: -0.0000

Data Index: 886339 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 3.1693. Min Range: -3.1693

Max Act: 2.3666. Min Act: -0.0000

Data Index: 456524 (C4 (Web Text))

Max Activating Token Index: 530

Text #9

Max Range: 3.1693. Min Range: -3.1693

Max Act: 2.3574. Min Act: -0.0000

Data Index: 1417735 (Python Code)

Max Activating Token Index: 419

Text #10

Max Range: 3.1693. Min Range: -3.1693

Max Act: 2.4430. Min Act: -0.0000

Data Index: 1510922 (Python Code)

Max Activating Token Index: 641

Text #11

Max Range: 3.1693. Min Range: -3.1693

Max Act: 2.3074. Min Act: -0.0000

Data Index: 549606 (C4 (Web Text))

Max Activating Token Index: 372

Text #12

Max Range: 3.1693. Min Range: -3.1693

Max Act: 2.4053. Min Act: -0.0000

Data Index: 1580224 (Python Code)

Max Activating Token Index: 49

Text #13

Max Range: 3.1693. Min Range: -3.1693

Max Act: 2.4795. Min Act: -0.0000

Data Index: 1586908 (Python Code)

Max Activating Token Index: 905

Text #14

Max Range: 3.1693. Min Range: -3.1693

Max Act: 2.1769. Min Act: -0.0000

Data Index: 1593799 (Python Code)

Max Activating Token Index: 113

Text #15

Max Range: 3.1693. Min Range: -3.1693

Max Act: 2.2494. Min Act: -0.0000

Data Index: 1435777 (Python Code)

Max Activating Token Index: 125

Text #16

Max Range: 3.1693. Min Range: -3.1693

Max Act: 2.3682. Min Act: -0.0000

Data Index: 1361776 (Python Code)

Max Activating Token Index: 999

Text #17

Max Range: 3.1693. Min Range: -3.1693

Max Act: 2.3169. Min Act: -0.0000

Data Index: 1561995 (Python Code)

Max Activating Token Index: 10

Text #18

Max Range: 3.1693. Min Range: -3.1693

Max Act: 2.1379. Min Act: -0.0000

Data Index: 1398603 (Python Code)

Max Activating Token Index: 14

Text #19

Max Range: 3.1693. Min Range: -3.1693

Max Act: 1.9933. Min Act: -0.0000

Data Index: 622683 (C4 (Web Text))

Max Activating Token Index: 242