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

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

Neuron 455 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6509. Min Range: -0.6509

Max Act: 0.6509. Min Act: -0.0001

Data Index: 404939 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 0.6509. Min Range: -0.6509

Max Act: 0.5110. Min Act: -0.0001

Data Index: 894860 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 0.6509. Min Range: -0.6509

Max Act: 0.4589. Min Act: -0.0001

Data Index: 1330718 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 0.6509. Min Range: -0.6509

Max Act: 0.4486. Min Act: -0.0001

Data Index: 559854 (C4 (Web Text))

Max Activating Token Index: 450

Text #4

Max Range: 0.6509. Min Range: -0.6509

Max Act: 0.4341. Min Act: -0.0001

Data Index: 91741 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 0.6509. Min Range: -0.6509

Max Act: 0.4442. Min Act: -0.0000

Data Index: 289833 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 0.6509. Min Range: -0.6509

Max Act: 0.4116. Min Act: -0.0000

Data Index: 34898 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 0.6509. Min Range: -0.6509

Max Act: 0.4258. Min Act: -0.0000

Data Index: 729355 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 0.6509. Min Range: -0.6509

Max Act: 0.4064. Min Act: -0.0001

Data Index: 636343 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 0.6509. Min Range: -0.6509

Max Act: 0.4177. Min Act: -0.0000

Data Index: 444879 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 0.6509. Min Range: -0.6509

Max Act: 0.4241. Min Act: -0.0001

Data Index: 1046298 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 0.6509. Min Range: -0.6509

Max Act: 0.4269. Min Act: -0.0001

Data Index: 458635 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 0.6509. Min Range: -0.6509

Max Act: 0.4004. Min Act: -0.0000

Data Index: 310877 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 0.6509. Min Range: -0.6509

Max Act: 0.4178. Min Act: -0.0001

Data Index: 755287 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 0.6509. Min Range: -0.6509

Max Act: 0.3642. Min Act: -0.0001

Data Index: 221785 (C4 (Web Text))

Max Activating Token Index: 983

Text #15

Max Range: 0.6509. Min Range: -0.6509

Max Act: 0.3845. Min Act: -0.0001

Data Index: 818424 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 0.6509. Min Range: -0.6509

Max Act: 0.3837. Min Act: -0.0001

Data Index: 452269 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 0.6509. Min Range: -0.6509

Max Act: 0.3830. Min Act: -0.0001

Data Index: 599198 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 0.6509. Min Range: -0.6509

Max Act: 0.3641. Min Act: -0.0000

Data Index: 1269453 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 0.6509. Min Range: -0.6509

Max Act: 0.3634. Min Act: -0.0000

Data Index: 235998 (C4 (Web Text))

Max Activating Token Index: 297