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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3970 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6526. Min Range: -0.6526

Max Act: 0.6526. Min Act: -0.0000

Data Index: 1287183 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 0.6526. Min Range: -0.6526

Max Act: 0.5286. Min Act: -0.0000

Data Index: 349589 (C4 (Web Text))

Max Activating Token Index: 1018

Text #2

Max Range: 0.6526. Min Range: -0.6526

Max Act: 0.4943. Min Act: -0.0000

Data Index: 399338 (C4 (Web Text))

Max Activating Token Index: 977

Text #3

Max Range: 0.6526. Min Range: -0.6526

Max Act: 0.5014. Min Act: -0.0000

Data Index: 175425 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 0.6526. Min Range: -0.6526

Max Act: 0.4849. Min Act: -0.0000

Data Index: 289725 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 0.6526. Min Range: -0.6526

Max Act: 0.5141. Min Act: -0.0000

Data Index: 1174348 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 0.6526. Min Range: -0.6526

Max Act: 0.4657. Min Act: -0.0000

Data Index: 967058 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 0.6526. Min Range: -0.6526

Max Act: 0.4547. Min Act: -0.0000

Data Index: 172867 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 0.6526. Min Range: -0.6526

Max Act: 0.4574. Min Act: -0.0000

Data Index: 599546 (C4 (Web Text))

Max Activating Token Index: 461

Text #9

Max Range: 0.6526. Min Range: -0.6526

Max Act: 0.4500. Min Act: -0.0000

Data Index: 946128 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 0.6526. Min Range: -0.6526

Max Act: 0.4367. Min Act: -0.0000

Data Index: 1084682 (C4 (Web Text))

Max Activating Token Index: 989

Text #11

Max Range: 0.6526. Min Range: -0.6526

Max Act: 0.3915. Min Act: -0.0000

Data Index: 1016510 (C4 (Web Text))

Max Activating Token Index: 934

Text #12

Max Range: 0.6526. Min Range: -0.6526

Max Act: 0.4169. Min Act: -0.0000

Data Index: 235090 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 0.6526. Min Range: -0.6526

Max Act: 0.4271. Min Act: -0.0000

Data Index: 1296604 (C4 (Web Text))

Max Activating Token Index: 548

Text #14

Max Range: 0.6526. Min Range: -0.6526

Max Act: 0.3605. Min Act: -0.0000

Data Index: 884455 (C4 (Web Text))

Max Activating Token Index: 858

Text #15

Max Range: 0.6526. Min Range: -0.6526

Max Act: 0.4160. Min Act: -0.0000

Data Index: 16369 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 0.6526. Min Range: -0.6526

Max Act: 0.4122. Min Act: -0.0000

Data Index: 1092637 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 0.6526. Min Range: -0.6526

Max Act: 0.3918. Min Act: -0.0000

Data Index: 8806 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 0.6526. Min Range: -0.6526

Max Act: 0.3878. Min Act: -0.0000

Data Index: 71209 (C4 (Web Text))

Max Activating Token Index: 575

Text #19

Max Range: 0.6526. Min Range: -0.6526

Max Act: 0.4088. Min Act: -0.0000

Data Index: 717119 (C4 (Web Text))

Max Activating Token Index: 233