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

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

Neuron 4484 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.6116. Min Act: -0.0000

Data Index: 1117888 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.6386. Min Act: -0.0000

Data Index: 327889 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5752. Min Act: -0.0000

Data Index: 294399 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5895. Min Act: -0.0000

Data Index: 575882 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5695. Min Act: -0.0000

Data Index: 223967 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5257. Min Act: -0.0000

Data Index: 107502 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5542. Min Act: -0.0000

Data Index: 1600232 (Python Code)

Max Activating Token Index: 432

Text #7

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5414. Min Act: -0.0000

Data Index: 440495 (C4 (Web Text))

Max Activating Token Index: 369

Text #8

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5301. Min Act: -0.0000

Data Index: 1421477 (Python Code)

Max Activating Token Index: 980

Text #9

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5466. Min Act: -0.0000

Data Index: 338336 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5071. Min Act: -0.0000

Data Index: 1228497 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5170. Min Act: -0.0000

Data Index: 662672 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5517. Min Act: -0.0000

Data Index: 844473 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5090. Min Act: -0.0000

Data Index: 554306 (C4 (Web Text))

Max Activating Token Index: 1002

Text #14

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5041. Min Act: -0.0000

Data Index: 1311934 (C4 (Web Text))

Max Activating Token Index: 439

Text #15

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5215. Min Act: -0.0000

Data Index: 1151374 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.4893. Min Act: -0.0000

Data Index: 517220 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5029. Min Act: -0.0000

Data Index: 764310 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5036. Min Act: -0.0000

Data Index: 862939 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.4839. Min Act: -0.0000

Data Index: 119231 (C4 (Web Text))

Max Activating Token Index: 665