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

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

Neuron 4720 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7597. Min Range: -1.7597

Max Act: 1.7597. Min Act: -0.0000

Data Index: 745445 (C4 (Web Text))

Max Activating Token Index: 822

Text #1

Max Range: 1.7597. Min Range: -1.7597

Max Act: 0.6287. Min Act: -0.0000

Data Index: 134455 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 1.7597. Min Range: -1.7597

Max Act: 0.5824. Min Act: -0.0000

Data Index: 1584138 (Python Code)

Max Activating Token Index: 706

Text #3

Max Range: 1.7597. Min Range: -1.7597

Max Act: 0.5504. Min Act: -0.0000

Data Index: 50519 (C4 (Web Text))

Max Activating Token Index: 413

Text #4

Max Range: 1.7597. Min Range: -1.7597

Max Act: 0.5532. Min Act: -0.0000

Data Index: 287276 (C4 (Web Text))

Max Activating Token Index: 958

Text #5

Max Range: 1.7597. Min Range: -1.7597

Max Act: 0.5043. Min Act: -0.0000

Data Index: 1443242 (Python Code)

Max Activating Token Index: 434

Text #6

Max Range: 1.7597. Min Range: -1.7597

Max Act: 0.5101. Min Act: -0.0000

Data Index: 1384441 (Python Code)

Max Activating Token Index: 496

Text #7

Max Range: 1.7597. Min Range: -1.7597

Max Act: 0.4947. Min Act: -0.0000

Data Index: 1465525 (Python Code)

Max Activating Token Index: 833

Text #8

Max Range: 1.7597. Min Range: -1.7597

Max Act: 0.5406. Min Act: -0.0000

Data Index: 135676 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 1.7597. Min Range: -1.7597

Max Act: 0.4834. Min Act: -0.0000

Data Index: 1646956 (Python Code)

Max Activating Token Index: 398

Text #10

Max Range: 1.7597. Min Range: -1.7597

Max Act: 0.5109. Min Act: -0.0000

Data Index: 344327 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 1.7597. Min Range: -1.7597

Max Act: 0.4802. Min Act: -0.0000

Data Index: 1405539 (Python Code)

Max Activating Token Index: 902

Text #12

Max Range: 1.7597. Min Range: -1.7597

Max Act: 0.4954. Min Act: -0.0000

Data Index: 258354 (C4 (Web Text))

Max Activating Token Index: 437

Text #13

Max Range: 1.7597. Min Range: -1.7597

Max Act: 0.4816. Min Act: -0.0000

Data Index: 1616231 (Python Code)

Max Activating Token Index: 176

Text #14

Max Range: 1.7597. Min Range: -1.7597

Max Act: 0.5064. Min Act: -0.0000

Data Index: 1582367 (Python Code)

Max Activating Token Index: 650

Text #15

Max Range: 1.7597. Min Range: -1.7597

Max Act: 0.4662. Min Act: -0.0000

Data Index: 1561766 (Python Code)

Max Activating Token Index: 593

Text #16

Max Range: 1.7597. Min Range: -1.7597

Max Act: 0.4808. Min Act: -0.0000

Data Index: 1521487 (Python Code)

Max Activating Token Index: 996

Text #17

Max Range: 1.7597. Min Range: -1.7597

Max Act: 0.5067. Min Act: -0.0000

Data Index: 741675 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 1.7597. Min Range: -1.7597

Max Act: 0.5027. Min Act: -0.0000

Data Index: 1491690 (Python Code)

Max Activating Token Index: 219

Text #19

Max Range: 1.7597. Min Range: -1.7597

Max Act: 0.4720. Min Act: -0.0000

Data Index: 1567972 (Python Code)

Max Activating Token Index: 270