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

Dataset: The Pile

Neuron 84 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: 0.7952. Min Range: -0.7952

Max Act: 0.7952. Min Act: -0.0000

Data Index: 589480 (The Pile)

Max Activating Token Index: 544

Text #1

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.6606. Min Act: -0.0000

Data Index: 999123 (The Pile)

Max Activating Token Index: 498

Text #2

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.6232. Min Act: -0.0000

Data Index: 607647 (The Pile)

Max Activating Token Index: 259

Text #3

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.6407. Min Act: -0.0000

Data Index: 490416 (The Pile)

Max Activating Token Index: 185

Text #4

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.6377. Min Act: -0.0000

Data Index: 1115232 (The Pile)

Max Activating Token Index: 836

Text #5

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.6544. Min Act: -0.0000

Data Index: 393001 (The Pile)

Max Activating Token Index: 339

Text #6

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.6271. Min Act: -0.0000

Data Index: 979348 (The Pile)

Max Activating Token Index: 248

Text #7

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.6298. Min Act: -0.0000

Data Index: 765069 (The Pile)

Max Activating Token Index: 199

Text #8

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.5563. Min Act: -0.0000

Data Index: 1927256 (The Pile)

Max Activating Token Index: 539

Text #9

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.6196. Min Act: -0.0000

Data Index: 1187045 (The Pile)

Max Activating Token Index: 705

Text #10

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.6020. Min Act: -0.0000

Data Index: 1702209 (The Pile)

Max Activating Token Index: 613

Text #11

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.6221. Min Act: -0.0000

Data Index: 1649265 (The Pile)

Max Activating Token Index: 927

Text #12

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.6564. Min Act: -0.0000

Data Index: 858978 (The Pile)

Max Activating Token Index: 880

Text #13

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.6131. Min Act: -0.0000

Data Index: 1858580 (The Pile)

Max Activating Token Index: 974

Text #14

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.6307. Min Act: -0.0000

Data Index: 1941547 (The Pile)

Max Activating Token Index: 112

Text #15

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.6708. Min Act: -0.0000

Data Index: 1758895 (The Pile)

Max Activating Token Index: 633

Text #16

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.6036. Min Act: -0.0000

Data Index: 1815574 (The Pile)

Max Activating Token Index: 34

Text #17

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.6055. Min Act: -0.0000

Data Index: 596526 (The Pile)

Max Activating Token Index: 761

Text #18

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.5981. Min Act: -0.0000

Data Index: 1976447 (The Pile)

Max Activating Token Index: 746

Text #19

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.5543. Min Act: -0.0000

Data Index: 450621 (The Pile)

Max Activating Token Index: 594