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

Dataset: The Pile

Neuron 2067 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1751. Min Range: -1.1751

Max Act: 1.1751. Min Act: -0.0000

Data Index: 1742438 (The Pile)

Max Activating Token Index: 651

Text #1

Max Range: 1.1751. Min Range: -1.1751

Max Act: 1.0365. Min Act: -0.0000

Data Index: 369503 (The Pile)

Max Activating Token Index: 418

Text #2

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.9972. Min Act: -0.0000

Data Index: 1384175 (The Pile)

Max Activating Token Index: 9

Text #3

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.8793. Min Act: -0.0000

Data Index: 564108 (The Pile)

Max Activating Token Index: 178

Text #4

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.8648. Min Act: -0.0000

Data Index: 197948 (The Pile)

Max Activating Token Index: 582

Text #5

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.8595. Min Act: -0.0000

Data Index: 51510 (The Pile)

Max Activating Token Index: 575

Text #6

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.8419. Min Act: -0.0000

Data Index: 1494919 (The Pile)

Max Activating Token Index: 507

Text #7

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.8467. Min Act: -0.0000

Data Index: 327043 (The Pile)

Max Activating Token Index: 708

Text #8

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.7062. Min Act: -0.0000

Data Index: 227600 (The Pile)

Max Activating Token Index: 29

Text #9

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.6866. Min Act: -0.0000

Data Index: 475290 (The Pile)

Max Activating Token Index: 268

Text #10

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.6753. Min Act: -0.0000

Data Index: 119585 (The Pile)

Max Activating Token Index: 766

Text #11

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.7201. Min Act: -0.0000

Data Index: 594773 (The Pile)

Max Activating Token Index: 271

Text #12

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.6276. Min Act: -0.0000

Data Index: 912862 (The Pile)

Max Activating Token Index: 6

Text #13

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.7346. Min Act: -0.0000

Data Index: 159000 (The Pile)

Max Activating Token Index: 197

Text #14

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.6464. Min Act: -0.0000

Data Index: 1370807 (The Pile)

Max Activating Token Index: 152

Text #15

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.7121. Min Act: -0.0000

Data Index: 38624 (The Pile)

Max Activating Token Index: 860

Text #16

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.5884. Min Act: -0.0000

Data Index: 779833 (The Pile)

Max Activating Token Index: 499

Text #17

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.6864. Min Act: -0.0000

Data Index: 24169 (The Pile)

Max Activating Token Index: 13

Text #18

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.6453. Min Act: -0.0000

Data Index: 1820779 (The Pile)

Max Activating Token Index: 334

Text #19

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.6005. Min Act: -0.0000

Data Index: 1146837 (The Pile)

Max Activating Token Index: 898