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

Dataset: The Pile

Neuron 4775 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: 1.1249. Min Range: -1.1249

Max Act: 1.1249. Min Act: -0.0000

Data Index: 447735 (The Pile)

Max Activating Token Index: 316

Text #1

Max Range: 1.1249. Min Range: -1.1249

Max Act: 1.0471. Min Act: -0.0000

Data Index: 903092 (The Pile)

Max Activating Token Index: 641

Text #2

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.9774. Min Act: -0.0000

Data Index: 1152026 (The Pile)

Max Activating Token Index: 137

Text #3

Max Range: 1.1249. Min Range: -1.1249

Max Act: 1.0012. Min Act: -0.0000

Data Index: 1133440 (The Pile)

Max Activating Token Index: 93

Text #4

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.9554. Min Act: -0.0000

Data Index: 1925310 (The Pile)

Max Activating Token Index: 461

Text #5

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.9153. Min Act: -0.0000

Data Index: 132418 (The Pile)

Max Activating Token Index: 511

Text #6

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.9151. Min Act: -0.0000

Data Index: 1742386 (The Pile)

Max Activating Token Index: 66

Text #7

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.7784. Min Act: -0.0000

Data Index: 1064972 (The Pile)

Max Activating Token Index: 836

Text #8

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.9196. Min Act: -0.0000

Data Index: 362147 (The Pile)

Max Activating Token Index: 612

Text #9

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.9144. Min Act: -0.0000

Data Index: 1527741 (The Pile)

Max Activating Token Index: 746

Text #10

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.8919. Min Act: -0.0000

Data Index: 1637409 (The Pile)

Max Activating Token Index: 429

Text #11

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.8479. Min Act: -0.0000

Data Index: 594107 (The Pile)

Max Activating Token Index: 104

Text #12

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.8824. Min Act: -0.0000

Data Index: 97728 (The Pile)

Max Activating Token Index: 43

Text #13

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.8872. Min Act: -0.0000

Data Index: 135830 (The Pile)

Max Activating Token Index: 21

Text #14

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.8468. Min Act: -0.0000

Data Index: 816685 (The Pile)

Max Activating Token Index: 551

Text #15

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.9130. Min Act: -0.0000

Data Index: 478318 (The Pile)

Max Activating Token Index: 618

Text #16

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.7549. Min Act: -0.0000

Data Index: 233774 (The Pile)

Max Activating Token Index: 325

Text #17

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.8449. Min Act: -0.0000

Data Index: 1800762 (The Pile)

Max Activating Token Index: 26

Text #18

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.7528. Min Act: -0.0000

Data Index: 1344328 (The Pile)

Max Activating Token Index: 663

Text #19

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.8441. Min Act: -0.0000

Data Index: 403973 (The Pile)

Max Activating Token Index: 599