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

Dataset: The Pile

Neuron 3430 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.8437. Min Act: -0.0000

Data Index: 936564 (The Pile)

Max Activating Token Index: 758

Text #1

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.7481. Min Act: -0.0000

Data Index: 1039741 (The Pile)

Max Activating Token Index: 256

Text #2

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.7462. Min Act: -0.0000

Data Index: 1735539 (The Pile)

Max Activating Token Index: 717

Text #3

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.6860. Min Act: -0.0000

Data Index: 63034 (The Pile)

Max Activating Token Index: 376

Text #4

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.6910. Min Act: -0.0000

Data Index: 651070 (The Pile)

Max Activating Token Index: 884

Text #5

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.4746. Min Act: -0.0000

Data Index: 1236666 (The Pile)

Max Activating Token Index: 904

Text #6

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.6418. Min Act: -0.0000

Data Index: 128594 (The Pile)

Max Activating Token Index: 751

Text #7

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.7023. Min Act: -0.0000

Data Index: 1171515 (The Pile)

Max Activating Token Index: 195

Text #8

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.6662. Min Act: -0.0000

Data Index: 268468 (The Pile)

Max Activating Token Index: 404

Text #9

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.6866. Min Act: -0.0000

Data Index: 1367873 (The Pile)

Max Activating Token Index: 520

Text #10

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.6713. Min Act: -0.0000

Data Index: 411529 (The Pile)

Max Activating Token Index: 911

Text #11

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.6461. Min Act: -0.0000

Data Index: 1702038 (The Pile)

Max Activating Token Index: 153

Text #12

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.6701. Min Act: -0.0000

Data Index: 291584 (The Pile)

Max Activating Token Index: 888

Text #13

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.6417. Min Act: -0.0000

Data Index: 1996015 (The Pile)

Max Activating Token Index: 991

Text #14

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.6104. Min Act: -0.0000

Data Index: 159316 (The Pile)

Max Activating Token Index: 492

Text #15

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.6142. Min Act: -0.0000

Data Index: 1804572 (The Pile)

Max Activating Token Index: 1001

Text #16

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.6326. Min Act: -0.0000

Data Index: 1686434 (The Pile)

Max Activating Token Index: 506

Text #17

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.6491. Min Act: -0.0000

Data Index: 1725235 (The Pile)

Max Activating Token Index: 174

Text #18

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.6108. Min Act: -0.0000

Data Index: 1462102 (The Pile)

Max Activating Token Index: 414

Text #19

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.5872. Min Act: -0.0000

Data Index: 724713 (The Pile)

Max Activating Token Index: 312