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

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

Neuron 3422 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2643. Min Range: -3.2643

Max Act: 3.2643. Min Act: -0.0000

Data Index: 1516899 (Python Code)

Max Activating Token Index: 654

Text #1

Max Range: 3.2643. Min Range: -3.2643

Max Act: 2.6344. Min Act: -0.0000

Data Index: 1106402 (C4 (Web Text))

Max Activating Token Index: 965

Text #2

Max Range: 3.2643. Min Range: -3.2643

Max Act: 2.6351. Min Act: -0.0000

Data Index: 1518358 (Python Code)

Max Activating Token Index: 554

Text #3

Max Range: 3.2643. Min Range: -3.2643

Max Act: 2.6640. Min Act: -0.0000

Data Index: 1518594 (Python Code)

Max Activating Token Index: 569

Text #4

Max Range: 3.2643. Min Range: -3.2643

Max Act: 2.7511. Min Act: -0.0000

Data Index: 1162405 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 3.2643. Min Range: -3.2643

Max Act: 2.5931. Min Act: -0.0000

Data Index: 1497066 (Python Code)

Max Activating Token Index: 26

Text #6

Max Range: 3.2643. Min Range: -3.2643

Max Act: 2.4201. Min Act: -0.0000

Data Index: 958678 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 3.2643. Min Range: -3.2643

Max Act: 2.3602. Min Act: -0.0000

Data Index: 905982 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 3.2643. Min Range: -3.2643

Max Act: 2.3601. Min Act: -0.0000

Data Index: 319131 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 3.2643. Min Range: -3.2643

Max Act: 2.4206. Min Act: -0.0000

Data Index: 1365994 (Python Code)

Max Activating Token Index: 356

Text #10

Max Range: 3.2643. Min Range: -3.2643

Max Act: 2.4689. Min Act: -0.0000

Data Index: 1249660 (C4 (Web Text))

Max Activating Token Index: 1016

Text #11

Max Range: 3.2643. Min Range: -3.2643

Max Act: 2.3433. Min Act: -0.0000

Data Index: 1276609 (C4 (Web Text))

Max Activating Token Index: 820

Text #12

Max Range: 3.2643. Min Range: -3.2643

Max Act: 2.4665. Min Act: -0.0000

Data Index: 1625470 (Python Code)

Max Activating Token Index: 240

Text #13

Max Range: 3.2643. Min Range: -3.2643

Max Act: 2.1971. Min Act: -0.0000

Data Index: 1466959 (Python Code)

Max Activating Token Index: 502

Text #14

Max Range: 3.2643. Min Range: -3.2643

Max Act: 2.1968. Min Act: -0.0000

Data Index: 1427202 (Python Code)

Max Activating Token Index: 248

Text #15

Max Range: 3.2643. Min Range: -3.2643

Max Act: 2.4273. Min Act: -0.0000

Data Index: 1524659 (Python Code)

Max Activating Token Index: 835

Text #16

Max Range: 3.2643. Min Range: -3.2643

Max Act: 2.1570. Min Act: -0.0000

Data Index: 978426 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 3.2643. Min Range: -3.2643

Max Act: 2.3705. Min Act: -0.0000

Data Index: 1017987 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 3.2643. Min Range: -3.2643

Max Act: 2.2401. Min Act: -0.0000

Data Index: 1449472 (Python Code)

Max Activating Token Index: 77

Text #19

Max Range: 3.2643. Min Range: -3.2643

Max Act: 2.0646. Min Act: -0.0000

Data Index: 1419718 (Python Code)

Max Activating Token Index: 828