Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1311 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.8437. Min Act: -0.0000

Data Index: 1474411 (The Pile)

Max Activating Token Index: 350

Text #1

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.7745. Min Act: -0.0000

Data Index: 849400 (The Pile)

Max Activating Token Index: 201

Text #2

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.7881. Min Act: -0.0000

Data Index: 335197 (The Pile)

Max Activating Token Index: 254

Text #3

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.7088. Min Act: -0.0000

Data Index: 315389 (The Pile)

Max Activating Token Index: 681

Text #4

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.7685. Min Act: -0.0000

Data Index: 663386 (The Pile)

Max Activating Token Index: 641

Text #5

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.7097. Min Act: -0.0000

Data Index: 1392060 (The Pile)

Max Activating Token Index: 408

Text #6

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.7220. Min Act: -0.0000

Data Index: 1033539 (The Pile)

Max Activating Token Index: 31

Text #7

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.7347. Min Act: -0.0000

Data Index: 1113319 (The Pile)

Max Activating Token Index: 308

Text #8

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.6867. Min Act: -0.0000

Data Index: 1171418 (The Pile)

Max Activating Token Index: 291

Text #9

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.6861. Min Act: -0.0000

Data Index: 513295 (The Pile)

Max Activating Token Index: 290

Text #10

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.7053. Min Act: -0.0000

Data Index: 784710 (The Pile)

Max Activating Token Index: 172

Text #11

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.6743. Min Act: -0.0000

Data Index: 1402241 (The Pile)

Max Activating Token Index: 299

Text #12

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.7196. Min Act: -0.0000

Data Index: 707999 (The Pile)

Max Activating Token Index: 1011

Text #13

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.6812. Min Act: -0.0000

Data Index: 283203 (The Pile)

Max Activating Token Index: 648

Text #14

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.6411. Min Act: -0.0000

Data Index: 1952103 (The Pile)

Max Activating Token Index: 335

Text #15

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.6444. Min Act: -0.0000

Data Index: 1414137 (The Pile)

Max Activating Token Index: 262

Text #16

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.6752. Min Act: -0.0000

Data Index: 669696 (The Pile)

Max Activating Token Index: 275

Text #17

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.6087. Min Act: -0.0000

Data Index: 1311913 (The Pile)

Max Activating Token Index: 52

Text #18

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.6536. Min Act: -0.0000

Data Index: 1874260 (The Pile)

Max Activating Token Index: 414

Text #19

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.6102. Min Act: -0.0000

Data Index: 324565 (The Pile)

Max Activating Token Index: 192