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

Dataset: The Pile

Neuron 3819 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: 1.9532. Min Range: -1.9532

Max Act: 1.9532. Min Act: -0.0000

Data Index: 676310 (The Pile)

Max Activating Token Index: 781

Text #1

Max Range: 1.9532. Min Range: -1.9532

Max Act: 1.3325. Min Act: -0.0000

Data Index: 333486 (The Pile)

Max Activating Token Index: 669

Text #2

Max Range: 1.9532. Min Range: -1.9532

Max Act: 1.5350. Min Act: -0.0000

Data Index: 605512 (The Pile)

Max Activating Token Index: 85

Text #3

Max Range: 1.9532. Min Range: -1.9532

Max Act: 1.6300. Min Act: -0.0000

Data Index: 1676428 (The Pile)

Max Activating Token Index: 198

Text #4

Max Range: 1.9532. Min Range: -1.9532

Max Act: 1.6769. Min Act: -0.0000

Data Index: 382393 (The Pile)

Max Activating Token Index: 969

Text #5

Max Range: 1.9532. Min Range: -1.9532

Max Act: 1.5358. Min Act: -0.0000

Data Index: 771273 (The Pile)

Max Activating Token Index: 236

Text #6

Max Range: 1.9532. Min Range: -1.9532

Max Act: 1.3480. Min Act: -0.0000

Data Index: 798093 (The Pile)

Max Activating Token Index: 236

Text #7

Max Range: 1.9532. Min Range: -1.9532

Max Act: 1.3954. Min Act: -0.0000

Data Index: 1474969 (The Pile)

Max Activating Token Index: 280

Text #8

Max Range: 1.9532. Min Range: -1.9532

Max Act: 1.3786. Min Act: -0.0000

Data Index: 480338 (The Pile)

Max Activating Token Index: 420

Text #9

Max Range: 1.9532. Min Range: -1.9532

Max Act: 1.2504. Min Act: -0.0000

Data Index: 888520 (The Pile)

Max Activating Token Index: 574

Text #10

Max Range: 1.9532. Min Range: -1.9532

Max Act: 1.1246. Min Act: -0.0000

Data Index: 211417 (The Pile)

Max Activating Token Index: 695

Text #11

Max Range: 1.9532. Min Range: -1.9532

Max Act: 1.3272. Min Act: -0.0000

Data Index: 1209666 (The Pile)

Max Activating Token Index: 211

Text #12

Max Range: 1.9532. Min Range: -1.9532

Max Act: 1.1429. Min Act: -0.0000

Data Index: 611008 (The Pile)

Max Activating Token Index: 209

Text #13

Max Range: 1.9532. Min Range: -1.9532

Max Act: 1.2683. Min Act: -0.0000

Data Index: 773794 (The Pile)

Max Activating Token Index: 237

Text #14

Max Range: 1.9532. Min Range: -1.9532

Max Act: 1.1256. Min Act: -0.0000

Data Index: 147706 (The Pile)

Max Activating Token Index: 646

Text #15

Max Range: 1.9532. Min Range: -1.9532

Max Act: 1.1016. Min Act: -0.0000

Data Index: 149469 (The Pile)

Max Activating Token Index: 1020

Text #16

Max Range: 1.9532. Min Range: -1.9532

Max Act: 1.1970. Min Act: -0.0000

Data Index: 696973 (The Pile)

Max Activating Token Index: 426

Text #17

Max Range: 1.9532. Min Range: -1.9532

Max Act: 1.1172. Min Act: -0.0000

Data Index: 1280615 (The Pile)

Max Activating Token Index: 959

Text #18

Max Range: 1.9532. Min Range: -1.9532

Max Act: 1.0123. Min Act: -0.0000

Data Index: 1867225 (The Pile)

Max Activating Token Index: 933

Text #19

Max Range: 1.9532. Min Range: -1.9532

Max Act: 0.9695. Min Act: -0.0000

Data Index: 1160091 (The Pile)

Max Activating Token Index: 356