Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 58 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0706. Min Act: -0.0000

Data Index: 610271 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0718. Min Act: -0.0001

Data Index: 89687 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0704. Min Act: -0.0001

Data Index: 627551 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0536. Min Act: -0.0001

Data Index: 358875 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0536. Min Act: -0.0000

Data Index: 350302 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0511. Min Act: -0.0001

Data Index: 1536718 (Python Code)

Max Activating Token Index: 865

Text #6

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0526. Min Act: -0.0001

Data Index: 668863 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0546. Min Act: -0.0001

Data Index: 730294 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0471. Min Act: -0.0001

Data Index: 1387697 (Python Code)

Max Activating Token Index: 358

Text #9

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0474. Min Act: -0.0001

Data Index: 1387732 (Python Code)

Max Activating Token Index: 957

Text #10

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0473. Min Act: -0.0000

Data Index: 458693 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0486. Min Act: -0.0000

Data Index: 585984 (C4 (Web Text))

Max Activating Token Index: 701

Text #12

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0447. Min Act: -0.0000

Data Index: 810086 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0463. Min Act: -0.0001

Data Index: 298515 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0432. Min Act: -0.0000

Data Index: 22478 (C4 (Web Text))

Max Activating Token Index: 525

Text #15

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0442. Min Act: -0.0001

Data Index: 807030 (C4 (Web Text))

Max Activating Token Index: 487

Text #16

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0430. Min Act: -0.0001

Data Index: 1605004 (Python Code)

Max Activating Token Index: 705

Text #17

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0460. Min Act: -0.0000

Data Index: 197840 (C4 (Web Text))

Max Activating Token Index: 510

Text #18

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0424. Min Act: -0.0001

Data Index: 327440 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0423. Min Act: -0.0001

Data Index: 1411087 (Python Code)

Max Activating Token Index: 590