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

Dataset: The Pile

Neuron 2563 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: 0.9365. Min Range: -0.9365

Max Act: 0.9365. Min Act: -0.0000

Data Index: 1287248 (The Pile)

Max Activating Token Index: 611

Text #1

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.9053. Min Act: -0.0000

Data Index: 1686036 (The Pile)

Max Activating Token Index: 871

Text #2

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.8542. Min Act: -0.0000

Data Index: 619581 (The Pile)

Max Activating Token Index: 789

Text #3

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.8626. Min Act: -0.0000

Data Index: 1670007 (The Pile)

Max Activating Token Index: 11

Text #4

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.8761. Min Act: -0.0000

Data Index: 551990 (The Pile)

Max Activating Token Index: 533

Text #5

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.9097. Min Act: -0.0000

Data Index: 1686938 (The Pile)

Max Activating Token Index: 116

Text #6

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7847. Min Act: -0.0000

Data Index: 451267 (The Pile)

Max Activating Token Index: 261

Text #7

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7711. Min Act: -0.0000

Data Index: 1717213 (The Pile)

Max Activating Token Index: 603

Text #8

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7646. Min Act: -0.0000

Data Index: 1448901 (The Pile)

Max Activating Token Index: 656

Text #9

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7218. Min Act: -0.0000

Data Index: 202455 (The Pile)

Max Activating Token Index: 593

Text #10

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7252. Min Act: -0.0000

Data Index: 1230056 (The Pile)

Max Activating Token Index: 137

Text #11

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7127. Min Act: -0.0000

Data Index: 854112 (The Pile)

Max Activating Token Index: 285

Text #12

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7034. Min Act: -0.0000

Data Index: 1271745 (The Pile)

Max Activating Token Index: 560

Text #13

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7567. Min Act: -0.0000

Data Index: 1097321 (The Pile)

Max Activating Token Index: 217

Text #14

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7276. Min Act: -0.0000

Data Index: 804060 (The Pile)

Max Activating Token Index: 348

Text #15

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6799. Min Act: -0.0000

Data Index: 260376 (The Pile)

Max Activating Token Index: 55

Text #16

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6969. Min Act: -0.0000

Data Index: 1020232 (The Pile)

Max Activating Token Index: 522

Text #17

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6808. Min Act: -0.0000

Data Index: 1195163 (The Pile)

Max Activating Token Index: 571

Text #18

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6387. Min Act: -0.0000

Data Index: 653861 (The Pile)

Max Activating Token Index: 135

Text #19

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6777. Min Act: -0.0000

Data Index: 487158 (The Pile)

Max Activating Token Index: 883