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

Dataset: The Pile

Neuron 323 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.5222. Min Act: -0.0000

Data Index: 1189280 (The Pile)

Max Activating Token Index: 738

Text #1

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4421. Min Act: -0.0000

Data Index: 624864 (The Pile)

Max Activating Token Index: 482

Text #2

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4047. Min Act: -0.0000

Data Index: 1072557 (The Pile)

Max Activating Token Index: 62

Text #3

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4168. Min Act: -0.0000

Data Index: 1409509 (The Pile)

Max Activating Token Index: 55

Text #4

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.3796. Min Act: -0.0000

Data Index: 1735583 (The Pile)

Max Activating Token Index: 796

Text #5

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.3509. Min Act: -0.0000

Data Index: 550542 (The Pile)

Max Activating Token Index: 572

Text #6

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.3604. Min Act: -0.0000

Data Index: 136127 (The Pile)

Max Activating Token Index: 491

Text #7

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.3641. Min Act: -0.0000

Data Index: 109442 (The Pile)

Max Activating Token Index: 480

Text #8

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.3795. Min Act: -0.0000

Data Index: 89469 (The Pile)

Max Activating Token Index: 880

Text #9

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.3282. Min Act: -0.0000

Data Index: 397275 (The Pile)

Max Activating Token Index: 982

Text #10

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.3589. Min Act: -0.0000

Data Index: 1374218 (The Pile)

Max Activating Token Index: 811

Text #11

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.3596. Min Act: -0.0000

Data Index: 1505783 (The Pile)

Max Activating Token Index: 685

Text #12

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.3067. Min Act: -0.0000

Data Index: 1756237 (The Pile)

Max Activating Token Index: 106

Text #13

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.3350. Min Act: -0.0000

Data Index: 1156048 (The Pile)

Max Activating Token Index: 369

Text #14

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.3136. Min Act: -0.0000

Data Index: 600237 (The Pile)

Max Activating Token Index: 101

Text #15

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.3473. Min Act: -0.0000

Data Index: 838218 (The Pile)

Max Activating Token Index: 174

Text #16

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.3747. Min Act: -0.0000

Data Index: 1018082 (The Pile)

Max Activating Token Index: 879

Text #17

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.3948. Min Act: -0.0000

Data Index: 423649 (The Pile)

Max Activating Token Index: 753

Text #18

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.3118. Min Act: -0.0000

Data Index: 1234289 (The Pile)

Max Activating Token Index: 1008

Text #19

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.3291. Min Act: -0.0000

Data Index: 215260 (The Pile)

Max Activating Token Index: 889