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

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

Neuron 1394 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8652. Min Range: -2.8652

Max Act: 2.8652. Min Act: -0.0000

Data Index: 1077914 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 2.8652. Min Range: -2.8652

Max Act: 1.7757. Min Act: -0.0000

Data Index: 657939 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 2.8652. Min Range: -2.8652

Max Act: 1.6731. Min Act: -0.0000

Data Index: 968620 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 2.8652. Min Range: -2.8652

Max Act: 1.6018. Min Act: -0.0000

Data Index: 1228605 (C4 (Web Text))

Max Activating Token Index: 984

Text #4

Max Range: 2.8652. Min Range: -2.8652

Max Act: 1.5772. Min Act: -0.0000

Data Index: 1562744 (Python Code)

Max Activating Token Index: 647

Text #5

Max Range: 2.8652. Min Range: -2.8652

Max Act: 1.5411. Min Act: -0.0000

Data Index: 199297 (C4 (Web Text))

Max Activating Token Index: 301

Text #6

Max Range: 2.8652. Min Range: -2.8652

Max Act: 1.5669. Min Act: -0.0000

Data Index: 955025 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 2.8652. Min Range: -2.8652

Max Act: 1.5637. Min Act: -0.0000

Data Index: 731919 (C4 (Web Text))

Max Activating Token Index: 581

Text #8

Max Range: 2.8652. Min Range: -2.8652

Max Act: 1.4587. Min Act: -0.0000

Data Index: 141529 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 2.8652. Min Range: -2.8652

Max Act: 1.5018. Min Act: -0.0000

Data Index: 32585 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 2.8652. Min Range: -2.8652

Max Act: 1.2729. Min Act: -0.0000

Data Index: 318426 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 2.8652. Min Range: -2.8652

Max Act: 1.3106. Min Act: -0.0000

Data Index: 741571 (C4 (Web Text))

Max Activating Token Index: 632

Text #12

Max Range: 2.8652. Min Range: -2.8652

Max Act: 1.3533. Min Act: -0.0000

Data Index: 67698 (C4 (Web Text))

Max Activating Token Index: 558

Text #13

Max Range: 2.8652. Min Range: -2.8652

Max Act: 1.3624. Min Act: -0.0000

Data Index: 1224402 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 2.8652. Min Range: -2.8652

Max Act: 1.4141. Min Act: -0.0000

Data Index: 291263 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 2.8652. Min Range: -2.8652

Max Act: 1.1789. Min Act: -0.0000

Data Index: 145661 (C4 (Web Text))

Max Activating Token Index: 806

Text #16

Max Range: 2.8652. Min Range: -2.8652

Max Act: 1.3332. Min Act: -0.0000

Data Index: 468915 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 2.8652. Min Range: -2.8652

Max Act: 1.2127. Min Act: -0.0000

Data Index: 317627 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 2.8652. Min Range: -2.8652

Max Act: 1.3222. Min Act: -0.0000

Data Index: 1137145 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 2.8652. Min Range: -2.8652

Max Act: 1.3593. Min Act: -0.0000

Data Index: 991519 (C4 (Web Text))

Max Activating Token Index: 314