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

Dataset: The Pile

Neuron 476 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: 0.8271. Min Range: -0.8271

Max Act: 0.8271. Min Act: -0.0000

Data Index: 1860969 (The Pile)

Max Activating Token Index: 476

Text #1

Max Range: 0.8271. Min Range: -0.8271

Max Act: 0.8131. Min Act: -0.0000

Data Index: 1489856 (The Pile)

Max Activating Token Index: 427

Text #2

Max Range: 0.8271. Min Range: -0.8271

Max Act: 0.7507. Min Act: -0.0000

Data Index: 1749734 (The Pile)

Max Activating Token Index: 1002

Text #3

Max Range: 0.8271. Min Range: -0.8271

Max Act: 0.6862. Min Act: -0.0000

Data Index: 789882 (The Pile)

Max Activating Token Index: 327

Text #4

Max Range: 0.8271. Min Range: -0.8271

Max Act: 0.6052. Min Act: -0.0000

Data Index: 862670 (The Pile)

Max Activating Token Index: 895

Text #5

Max Range: 0.8271. Min Range: -0.8271

Max Act: 0.6512. Min Act: -0.0000

Data Index: 753228 (The Pile)

Max Activating Token Index: 793

Text #6

Max Range: 0.8271. Min Range: -0.8271

Max Act: 0.6797. Min Act: -0.0000

Data Index: 1149455 (The Pile)

Max Activating Token Index: 957

Text #7

Max Range: 0.8271. Min Range: -0.8271

Max Act: 0.6555. Min Act: -0.0000

Data Index: 471618 (The Pile)

Max Activating Token Index: 168

Text #8

Max Range: 0.8271. Min Range: -0.8271

Max Act: 0.6650. Min Act: -0.0000

Data Index: 552125 (The Pile)

Max Activating Token Index: 558

Text #9

Max Range: 0.8271. Min Range: -0.8271

Max Act: 0.6469. Min Act: -0.0000

Data Index: 1709549 (The Pile)

Max Activating Token Index: 77

Text #10

Max Range: 0.8271. Min Range: -0.8271

Max Act: 0.6657. Min Act: -0.0000

Data Index: 674734 (The Pile)

Max Activating Token Index: 509

Text #11

Max Range: 0.8271. Min Range: -0.8271

Max Act: 0.6599. Min Act: -0.0000

Data Index: 1208806 (The Pile)

Max Activating Token Index: 112

Text #12

Max Range: 0.8271. Min Range: -0.8271

Max Act: 0.6186. Min Act: -0.0000

Data Index: 1714286 (The Pile)

Max Activating Token Index: 473

Text #13

Max Range: 0.8271. Min Range: -0.8271

Max Act: 0.6579. Min Act: -0.0000

Data Index: 688373 (The Pile)

Max Activating Token Index: 855

Text #14

Max Range: 0.8271. Min Range: -0.8271

Max Act: 0.6369. Min Act: -0.0000

Data Index: 14313 (The Pile)

Max Activating Token Index: 346

Text #15

Max Range: 0.8271. Min Range: -0.8271

Max Act: 0.6474. Min Act: -0.0000

Data Index: 1238404 (The Pile)

Max Activating Token Index: 456

Text #16

Max Range: 0.8271. Min Range: -0.8271

Max Act: 0.6442. Min Act: -0.0000

Data Index: 1565690 (The Pile)

Max Activating Token Index: 469

Text #17

Max Range: 0.8271. Min Range: -0.8271

Max Act: 0.6278. Min Act: -0.0000

Data Index: 1933539 (The Pile)

Max Activating Token Index: 634

Text #18

Max Range: 0.8271. Min Range: -0.8271

Max Act: 0.6624. Min Act: -0.0000

Data Index: 110721 (The Pile)

Max Activating Token Index: 84

Text #19

Max Range: 0.8271. Min Range: -0.8271

Max Act: 0.5281. Min Act: -0.0000

Data Index: 1292535 (The Pile)

Max Activating Token Index: 805