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

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

Neuron 3605 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: 0.9823. Min Range: -0.9823

Max Act: 0.9823. Min Act: -0.0000

Data Index: 423661 (C4 (Web Text))

Max Activating Token Index: 528

Text #1

Max Range: 0.9823. Min Range: -0.9823

Max Act: 0.7965. Min Act: -0.0000

Data Index: 1652022 (Python Code)

Max Activating Token Index: 487

Text #2

Max Range: 0.9823. Min Range: -0.9823

Max Act: 0.8440. Min Act: -0.0000

Data Index: 22588 (C4 (Web Text))

Max Activating Token Index: 1012

Text #3

Max Range: 0.9823. Min Range: -0.9823

Max Act: 0.7490. Min Act: -0.0000

Data Index: 102179 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 0.9823. Min Range: -0.9823

Max Act: 0.7623. Min Act: -0.0000

Data Index: 709837 (C4 (Web Text))

Max Activating Token Index: 419

Text #5

Max Range: 0.9823. Min Range: -0.9823

Max Act: 0.7295. Min Act: -0.0000

Data Index: 1108525 (C4 (Web Text))

Max Activating Token Index: 242

Text #6

Max Range: 0.9823. Min Range: -0.9823

Max Act: 0.7182. Min Act: -0.0000

Data Index: 1182345 (C4 (Web Text))

Max Activating Token Index: 368

Text #7

Max Range: 0.9823. Min Range: -0.9823

Max Act: 0.7396. Min Act: -0.0000

Data Index: 973697 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 0.9823. Min Range: -0.9823

Max Act: 0.7456. Min Act: -0.0000

Data Index: 988504 (C4 (Web Text))

Max Activating Token Index: 310

Text #9

Max Range: 0.9823. Min Range: -0.9823

Max Act: 0.7239. Min Act: -0.0000

Data Index: 896590 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 0.9823. Min Range: -0.9823

Max Act: 0.7488. Min Act: -0.0000

Data Index: 396639 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 0.9823. Min Range: -0.9823

Max Act: 0.7320. Min Act: -0.0000

Data Index: 1654594 (Python Code)

Max Activating Token Index: 209

Text #12

Max Range: 0.9823. Min Range: -0.9823

Max Act: 0.7048. Min Act: -0.0000

Data Index: 1518374 (Python Code)

Max Activating Token Index: 564

Text #13

Max Range: 0.9823. Min Range: -0.9823

Max Act: 0.7273. Min Act: -0.0000

Data Index: 1610772 (Python Code)

Max Activating Token Index: 283

Text #14

Max Range: 0.9823. Min Range: -0.9823

Max Act: 0.7007. Min Act: -0.0000

Data Index: 438216 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 0.9823. Min Range: -0.9823

Max Act: 0.6995. Min Act: 0.0000

Data Index: 39386 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 0.9823. Min Range: -0.9823

Max Act: 0.6927. Min Act: -0.0000

Data Index: 150882 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 0.9823. Min Range: -0.9823

Max Act: 0.7103. Min Act: -0.0000

Data Index: 1395034 (Python Code)

Max Activating Token Index: 425

Text #18

Max Range: 0.9823. Min Range: -0.9823

Max Act: 0.7116. Min Act: -0.0000

Data Index: 1193311 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 0.9823. Min Range: -0.9823

Max Act: 0.6519. Min Act: -0.0000

Data Index: 445478 (C4 (Web Text))

Max Activating Token Index: 272