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

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

Neuron 2847 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: 3.1762. Min Range: -3.1762

Max Act: 3.1762. Min Act: -0.0000

Data Index: 229336 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 3.1762. Min Range: -3.1762

Max Act: 2.7877. Min Act: -0.0000

Data Index: 1557548 (Python Code)

Max Activating Token Index: 612

Text #2

Max Range: 3.1762. Min Range: -3.1762

Max Act: 2.4732. Min Act: -0.0000

Data Index: 1449982 (Python Code)

Max Activating Token Index: 705

Text #3

Max Range: 3.1762. Min Range: -3.1762

Max Act: 3.0104. Min Act: -0.0000

Data Index: 1388052 (Python Code)

Max Activating Token Index: 815

Text #4

Max Range: 3.1762. Min Range: -3.1762

Max Act: 2.6288. Min Act: -0.0000

Data Index: 592150 (C4 (Web Text))

Max Activating Token Index: 714

Text #5

Max Range: 3.1762. Min Range: -3.1762

Max Act: 2.5842. Min Act: -0.0000

Data Index: 1481442 (Python Code)

Max Activating Token Index: 237

Text #6

Max Range: 3.1762. Min Range: -3.1762

Max Act: 2.4257. Min Act: -0.0000

Data Index: 1521848 (Python Code)

Max Activating Token Index: 591

Text #7

Max Range: 3.1762. Min Range: -3.1762

Max Act: 2.5346. Min Act: -0.0000

Data Index: 1502852 (Python Code)

Max Activating Token Index: 742

Text #8

Max Range: 3.1762. Min Range: -3.1762

Max Act: 2.5104. Min Act: -0.0000

Data Index: 1362702 (Python Code)

Max Activating Token Index: 418

Text #9

Max Range: 3.1762. Min Range: -3.1762

Max Act: 2.4447. Min Act: -0.0000

Data Index: 1607994 (Python Code)

Max Activating Token Index: 773

Text #10

Max Range: 3.1762. Min Range: -3.1762

Max Act: 2.2650. Min Act: -0.0000

Data Index: 1384764 (Python Code)

Max Activating Token Index: 174

Text #11

Max Range: 3.1762. Min Range: -3.1762

Max Act: 2.2324. Min Act: -0.0000

Data Index: 1592230 (Python Code)

Max Activating Token Index: 146

Text #12

Max Range: 3.1762. Min Range: -3.1762

Max Act: 2.2218. Min Act: -0.0000

Data Index: 1542790 (Python Code)

Max Activating Token Index: 404

Text #13

Max Range: 3.1762. Min Range: -3.1762

Max Act: 2.4503. Min Act: -0.0000

Data Index: 1433502 (Python Code)

Max Activating Token Index: 884

Text #14

Max Range: 3.1762. Min Range: -3.1762

Max Act: 2.4370. Min Act: -0.0000

Data Index: 1621339 (Python Code)

Max Activating Token Index: 97

Text #15

Max Range: 3.1762. Min Range: -3.1762

Max Act: 2.2719. Min Act: -0.0000

Data Index: 1552896 (Python Code)

Max Activating Token Index: 146

Text #16

Max Range: 3.1762. Min Range: -3.1762

Max Act: 2.2931. Min Act: -0.0000

Data Index: 419194 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 3.1762. Min Range: -3.1762

Max Act: 2.2731. Min Act: -0.0000

Data Index: 1519626 (Python Code)

Max Activating Token Index: 307

Text #18

Max Range: 3.1762. Min Range: -3.1762

Max Act: 2.2466. Min Act: -0.0000

Data Index: 1553161 (Python Code)

Max Activating Token Index: 64

Text #19

Max Range: 3.1762. Min Range: -3.1762

Max Act: 2.2298. Min Act: -0.0000

Data Index: 1376482 (Python Code)

Max Activating Token Index: 16