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

Dataset: The Pile

Neuron 1215 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2640. Min Range: -1.2640

Max Act: 1.2640. Min Act: -0.0000

Data Index: 317001 (The Pile)

Max Activating Token Index: 556

Text #1

Max Range: 1.2640. Min Range: -1.2640

Max Act: 1.0805. Min Act: -0.0000

Data Index: 1199496 (The Pile)

Max Activating Token Index: 156

Text #2

Max Range: 1.2640. Min Range: -1.2640

Max Act: 1.0239. Min Act: -0.0000

Data Index: 819266 (The Pile)

Max Activating Token Index: 763

Text #3

Max Range: 1.2640. Min Range: -1.2640

Max Act: 1.0417. Min Act: -0.0001

Data Index: 1305007 (The Pile)

Max Activating Token Index: 229

Text #4

Max Range: 1.2640. Min Range: -1.2640

Max Act: 0.9069. Min Act: -0.0000

Data Index: 1280634 (The Pile)

Max Activating Token Index: 501

Text #5

Max Range: 1.2640. Min Range: -1.2640

Max Act: 0.8333. Min Act: -0.0000

Data Index: 967008 (The Pile)

Max Activating Token Index: 593

Text #6

Max Range: 1.2640. Min Range: -1.2640

Max Act: 0.9660. Min Act: -0.0000

Data Index: 810429 (The Pile)

Max Activating Token Index: 221

Text #7

Max Range: 1.2640. Min Range: -1.2640

Max Act: 0.9578. Min Act: -0.0000

Data Index: 1506175 (The Pile)

Max Activating Token Index: 799

Text #8

Max Range: 1.2640. Min Range: -1.2640

Max Act: 1.0502. Min Act: -0.0000

Data Index: 1971560 (The Pile)

Max Activating Token Index: 251

Text #9

Max Range: 1.2640. Min Range: -1.2640

Max Act: 0.9150. Min Act: -0.0000

Data Index: 100664 (The Pile)

Max Activating Token Index: 343

Text #10

Max Range: 1.2640. Min Range: -1.2640

Max Act: 1.0073. Min Act: -0.0000

Data Index: 1286518 (The Pile)

Max Activating Token Index: 1008

Text #11

Max Range: 1.2640. Min Range: -1.2640

Max Act: 0.7813. Min Act: -0.0000

Data Index: 1827843 (The Pile)

Max Activating Token Index: 377

Text #12

Max Range: 1.2640. Min Range: -1.2640

Max Act: 0.9475. Min Act: -0.0000

Data Index: 1184178 (The Pile)

Max Activating Token Index: 200

Text #13

Max Range: 1.2640. Min Range: -1.2640

Max Act: 0.9217. Min Act: -0.0000

Data Index: 800323 (The Pile)

Max Activating Token Index: 964

Text #14

Max Range: 1.2640. Min Range: -1.2640

Max Act: 0.9240. Min Act: -0.0000

Data Index: 945128 (The Pile)

Max Activating Token Index: 644

Text #15

Max Range: 1.2640. Min Range: -1.2640

Max Act: 0.9283. Min Act: -0.0000

Data Index: 1211782 (The Pile)

Max Activating Token Index: 602

Text #16

Max Range: 1.2640. Min Range: -1.2640

Max Act: 0.8643. Min Act: -0.0000

Data Index: 381663 (The Pile)

Max Activating Token Index: 497

Text #17

Max Range: 1.2640. Min Range: -1.2640

Max Act: 0.8804. Min Act: -0.0000

Data Index: 1867600 (The Pile)

Max Activating Token Index: 150

Text #18

Max Range: 1.2640. Min Range: -1.2640

Max Act: 0.9087. Min Act: -0.0000

Data Index: 469050 (The Pile)

Max Activating Token Index: 109

Text #19

Max Range: 1.2640. Min Range: -1.2640

Max Act: 0.9682. Min Act: -0.0000

Data Index: 1445589 (The Pile)

Max Activating Token Index: 940