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

Dataset: The Pile

Neuron 2581 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0340. Min Range: -1.0340

Max Act: 1.0232. Min Act: -0.0000

Data Index: 889367 (The Pile)

Max Activating Token Index: 465

Text #1

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.9905. Min Act: -0.0000

Data Index: 481710 (The Pile)

Max Activating Token Index: 338

Text #2

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.9593. Min Act: -0.0000

Data Index: 1113735 (The Pile)

Max Activating Token Index: 562

Text #3

Max Range: 1.0340. Min Range: -1.0340

Max Act: 1.0012. Min Act: -0.0000

Data Index: 693599 (The Pile)

Max Activating Token Index: 3

Text #4

Max Range: 1.0340. Min Range: -1.0340

Max Act: 1.0340. Min Act: -0.0000

Data Index: 1024513 (The Pile)

Max Activating Token Index: 994

Text #5

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.8112. Min Act: -0.0000

Data Index: 1184358 (The Pile)

Max Activating Token Index: 981

Text #6

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.8341. Min Act: -0.0000

Data Index: 954655 (The Pile)

Max Activating Token Index: 4

Text #7

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.7357. Min Act: -0.0000

Data Index: 575707 (The Pile)

Max Activating Token Index: 221

Text #8

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.8136. Min Act: -0.0000

Data Index: 441565 (The Pile)

Max Activating Token Index: 57

Text #9

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.9272. Min Act: -0.0000

Data Index: 136724 (The Pile)

Max Activating Token Index: 319

Text #10

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.8782. Min Act: -0.0000

Data Index: 1637300 (The Pile)

Max Activating Token Index: 47

Text #11

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.7838. Min Act: -0.0000

Data Index: 906296 (The Pile)

Max Activating Token Index: 21

Text #12

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.6958. Min Act: -0.0000

Data Index: 527191 (The Pile)

Max Activating Token Index: 927

Text #13

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.7964. Min Act: -0.0000

Data Index: 1818766 (The Pile)

Max Activating Token Index: 409

Text #14

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.8543. Min Act: -0.0000

Data Index: 875071 (The Pile)

Max Activating Token Index: 653

Text #15

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.7584. Min Act: -0.0000

Data Index: 663292 (The Pile)

Max Activating Token Index: 836

Text #16

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.7493. Min Act: -0.0000

Data Index: 404487 (The Pile)

Max Activating Token Index: 897

Text #17

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.7491. Min Act: -0.0000

Data Index: 1450972 (The Pile)

Max Activating Token Index: 992

Text #18

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.7542. Min Act: -0.0000

Data Index: 1094763 (The Pile)

Max Activating Token Index: 403

Text #19

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.7372. Min Act: -0.0000

Data Index: 485373 (The Pile)

Max Activating Token Index: 725