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

Dataset: The Pile

Neuron 3798 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.7684. Min Act: -0.0000

Data Index: 1298103 (The Pile)

Max Activating Token Index: 944

Text #1

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.8319. Min Act: -0.0000

Data Index: 692078 (The Pile)

Max Activating Token Index: 1022

Text #2

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.7592. Min Act: -0.0000

Data Index: 272776 (The Pile)

Max Activating Token Index: 209

Text #3

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.7154. Min Act: -0.0000

Data Index: 17930 (The Pile)

Max Activating Token Index: 626

Text #4

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.7106. Min Act: -0.0000

Data Index: 794482 (The Pile)

Max Activating Token Index: 974

Text #5

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.7206. Min Act: -0.0000

Data Index: 1162480 (The Pile)

Max Activating Token Index: 155

Text #6

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.7252. Min Act: -0.0000

Data Index: 1116264 (The Pile)

Max Activating Token Index: 98

Text #7

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.6820. Min Act: -0.0000

Data Index: 1356809 (The Pile)

Max Activating Token Index: 986

Text #8

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.5759. Min Act: -0.0000

Data Index: 848944 (The Pile)

Max Activating Token Index: 963

Text #9

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.6497. Min Act: -0.0000

Data Index: 1497005 (The Pile)

Max Activating Token Index: 165

Text #10

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.6663. Min Act: -0.0000

Data Index: 3195 (The Pile)

Max Activating Token Index: 42

Text #11

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.6451. Min Act: -0.0000

Data Index: 594224 (The Pile)

Max Activating Token Index: 876

Text #12

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.7116. Min Act: -0.0000

Data Index: 259764 (The Pile)

Max Activating Token Index: 562

Text #13

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.6120. Min Act: -0.0000

Data Index: 549432 (The Pile)

Max Activating Token Index: 676

Text #14

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.6337. Min Act: -0.0000

Data Index: 1480400 (The Pile)

Max Activating Token Index: 370

Text #15

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.6195. Min Act: -0.0000

Data Index: 310329 (The Pile)

Max Activating Token Index: 255

Text #16

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.5824. Min Act: -0.0000

Data Index: 904681 (The Pile)

Max Activating Token Index: 619

Text #17

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.6413. Min Act: -0.0000

Data Index: 310982 (The Pile)

Max Activating Token Index: 294

Text #18

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.5998. Min Act: -0.0000

Data Index: 180923 (The Pile)

Max Activating Token Index: 435

Text #19

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.6199. Min Act: -0.0000

Data Index: 396376 (The Pile)

Max Activating Token Index: 651