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

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

Neuron 3541 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.4632. Min Act: -0.0000

Data Index: 1381038 (Python Code)

Max Activating Token Index: 812

Text #1

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.2728. Min Act: -0.0000

Data Index: 1542723 (Python Code)

Max Activating Token Index: 314

Text #2

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.1609. Min Act: -0.0000

Data Index: 1593694 (Python Code)

Max Activating Token Index: 401

Text #3

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.2262. Min Act: -0.0000

Data Index: 1525476 (Python Code)

Max Activating Token Index: 314

Text #4

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.1389. Min Act: -0.0000

Data Index: 1560403 (Python Code)

Max Activating Token Index: 633

Text #5

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.1682. Min Act: -0.0000

Data Index: 1413172 (Python Code)

Max Activating Token Index: 959

Text #6

Max Range: 1.4632. Min Range: -1.4632

Max Act: 0.9953. Min Act: -0.0000

Data Index: 1619960 (Python Code)

Max Activating Token Index: 389

Text #7

Max Range: 1.4632. Min Range: -1.4632

Max Act: 0.9304. Min Act: -0.0000

Data Index: 1526432 (Python Code)

Max Activating Token Index: 674

Text #8

Max Range: 1.4632. Min Range: -1.4632

Max Act: 0.9559. Min Act: -0.0000

Data Index: 1632267 (Python Code)

Max Activating Token Index: 587

Text #9

Max Range: 1.4632. Min Range: -1.4632

Max Act: 0.9083. Min Act: -0.0000

Data Index: 1396825 (Python Code)

Max Activating Token Index: 323

Text #10

Max Range: 1.4632. Min Range: -1.4632

Max Act: 0.8774. Min Act: -0.0000

Data Index: 1413692 (Python Code)

Max Activating Token Index: 886

Text #11

Max Range: 1.4632. Min Range: -1.4632

Max Act: 0.8310. Min Act: -0.0000

Data Index: 1457354 (Python Code)

Max Activating Token Index: 516

Text #12

Max Range: 1.4632. Min Range: -1.4632

Max Act: 0.8153. Min Act: -0.0000

Data Index: 1644297 (Python Code)

Max Activating Token Index: 104

Text #13

Max Range: 1.4632. Min Range: -1.4632

Max Act: 0.8410. Min Act: -0.0000

Data Index: 1537501 (Python Code)

Max Activating Token Index: 93

Text #14

Max Range: 1.4632. Min Range: -1.4632

Max Act: 0.7506. Min Act: -0.0000

Data Index: 1434210 (Python Code)

Max Activating Token Index: 537

Text #15

Max Range: 1.4632. Min Range: -1.4632

Max Act: 0.7314. Min Act: -0.0000

Data Index: 1370901 (Python Code)

Max Activating Token Index: 963

Text #16

Max Range: 1.4632. Min Range: -1.4632

Max Act: 0.7314. Min Act: -0.0000

Data Index: 1624321 (Python Code)

Max Activating Token Index: 176

Text #17

Max Range: 1.4632. Min Range: -1.4632

Max Act: 0.7176. Min Act: 0.0000

Data Index: 1421416 (Python Code)

Max Activating Token Index: 392

Text #18

Max Range: 1.4632. Min Range: -1.4632

Max Act: 0.6602. Min Act: -0.0000

Data Index: 576126 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 1.4632. Min Range: -1.4632

Max Act: 0.6788. Min Act: -0.0000

Data Index: 1546799 (Python Code)

Max Activating Token Index: 767