Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 591 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6342. Min Range: -0.6342

Max Act: 0.6342. Min Act: -0.0001

Data Index: 490761 (C4 (Web Text))

Max Activating Token Index: 897

Text #1

Max Range: 0.6342. Min Range: -0.6342

Max Act: 0.5889. Min Act: -0.0001

Data Index: 539045 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 0.6342. Min Range: -0.6342

Max Act: 0.5687. Min Act: -0.0001

Data Index: 24013 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 0.6342. Min Range: -0.6342

Max Act: 0.5613. Min Act: -0.0001

Data Index: 490367 (C4 (Web Text))

Max Activating Token Index: 677

Text #4

Max Range: 0.6342. Min Range: -0.6342

Max Act: 0.5404. Min Act: -0.0001

Data Index: 1205189 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 0.6342. Min Range: -0.6342

Max Act: 0.5597. Min Act: -0.0001

Data Index: 279004 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 0.6342. Min Range: -0.6342

Max Act: 0.5185. Min Act: -0.0001

Data Index: 259341 (C4 (Web Text))

Max Activating Token Index: 690

Text #7

Max Range: 0.6342. Min Range: -0.6342

Max Act: 0.4969. Min Act: -0.0001

Data Index: 258373 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 0.6342. Min Range: -0.6342

Max Act: 0.5314. Min Act: -0.0001

Data Index: 636636 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 0.6342. Min Range: -0.6342

Max Act: 0.5222. Min Act: -0.0001

Data Index: 819136 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 0.6342. Min Range: -0.6342

Max Act: 0.5172. Min Act: -0.0001

Data Index: 1100623 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 0.6342. Min Range: -0.6342

Max Act: 0.4890. Min Act: -0.0001

Data Index: 302309 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 0.6342. Min Range: -0.6342

Max Act: 0.4901. Min Act: -0.0001

Data Index: 828639 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 0.6342. Min Range: -0.6342

Max Act: 0.4715. Min Act: -0.0001

Data Index: 1037513 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 0.6342. Min Range: -0.6342

Max Act: 0.4977. Min Act: -0.0001

Data Index: 815411 (C4 (Web Text))

Max Activating Token Index: 515

Text #15

Max Range: 0.6342. Min Range: -0.6342

Max Act: 0.4664. Min Act: -0.0001

Data Index: 1160204 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 0.6342. Min Range: -0.6342

Max Act: 0.4395. Min Act: -0.0001

Data Index: 433323 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 0.6342. Min Range: -0.6342

Max Act: 0.4672. Min Act: -0.0001

Data Index: 274681 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 0.6342. Min Range: -0.6342

Max Act: 0.4627. Min Act: -0.0001

Data Index: 751171 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 0.6342. Min Range: -0.6342

Max Act: 0.4757. Min Act: -0.0001

Data Index: 827225 (C4 (Web Text))

Max Activating Token Index: 195