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

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

Neuron 4244 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1410. Min Range: -2.1410

Max Act: 2.1410. Min Act: -0.0000

Data Index: 1066849 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.7933. Min Act: -0.0000

Data Index: 97615 (C4 (Web Text))

Max Activating Token Index: 176

Text #2

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.6247. Min Act: -0.0000

Data Index: 323858 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.5767. Min Act: -0.0000

Data Index: 1559461 (Python Code)

Max Activating Token Index: 101

Text #4

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.4839. Min Act: -0.0000

Data Index: 1361940 (Python Code)

Max Activating Token Index: 688

Text #5

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.4148. Min Act: 0.0001

Data Index: 1636529 (Python Code)

Max Activating Token Index: 607

Text #6

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.3864. Min Act: -0.0000

Data Index: 1568469 (Python Code)

Max Activating Token Index: 451

Text #7

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.3783. Min Act: -0.0000

Data Index: 1656172 (Python Code)

Max Activating Token Index: 522

Text #8

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.3617. Min Act: -0.0000

Data Index: 1538559 (Python Code)

Max Activating Token Index: 335

Text #9

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.4149. Min Act: -0.0000

Data Index: 1459733 (Python Code)

Max Activating Token Index: 521

Text #10

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.2403. Min Act: -0.0000

Data Index: 517124 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.2900. Min Act: -0.0000

Data Index: 1508116 (Python Code)

Max Activating Token Index: 459

Text #12

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.2896. Min Act: -0.0000

Data Index: 99776 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.3530. Min Act: -0.0000

Data Index: 537329 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.1818. Min Act: -0.0000

Data Index: 1114565 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.2621. Min Act: -0.0000

Data Index: 1102542 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.3452. Min Act: -0.0000

Data Index: 1605345 (Python Code)

Max Activating Token Index: 390

Text #17

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.2681. Min Act: -0.0000

Data Index: 1407540 (Python Code)

Max Activating Token Index: 452

Text #18

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.2332. Min Act: -0.0000

Data Index: 1649817 (Python Code)

Max Activating Token Index: 519

Text #19

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.1407. Min Act: -0.0000

Data Index: 1620797 (Python Code)

Max Activating Token Index: 595