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

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

Neuron 793 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1775. Min Range: -1.1775

Max Act: 1.1775. Min Act: -0.0001

Data Index: 690276 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.7242. Min Act: -0.0001

Data Index: 727716 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.7367. Min Act: -0.0001

Data Index: 1522682 (Python Code)

Max Activating Token Index: 609

Text #3

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.6897. Min Act: -0.0001

Data Index: 1382817 (Python Code)

Max Activating Token Index: 25

Text #4

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.6222. Min Act: -0.0001

Data Index: 1291177 (C4 (Web Text))

Max Activating Token Index: 1019

Text #5

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.6662. Min Act: -0.0001

Data Index: 698817 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.5743. Min Act: -0.0001

Data Index: 1638340 (Python Code)

Max Activating Token Index: 42

Text #7

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.6402. Min Act: -0.0001

Data Index: 672860 (C4 (Web Text))

Max Activating Token Index: 588

Text #8

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.5642. Min Act: -0.0001

Data Index: 862118 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.6111. Min Act: -0.0001

Data Index: 1193412 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.5238. Min Act: -0.0001

Data Index: 1615574 (Python Code)

Max Activating Token Index: 536

Text #11

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.5512. Min Act: -0.0001

Data Index: 1050633 (C4 (Web Text))

Max Activating Token Index: 499

Text #12

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.5476. Min Act: -0.0001

Data Index: 1572281 (Python Code)

Max Activating Token Index: 437

Text #13

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.5281. Min Act: -0.0001

Data Index: 246354 (C4 (Web Text))

Max Activating Token Index: 332

Text #14

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.5558. Min Act: -0.0001

Data Index: 1216096 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.4916. Min Act: -0.0001

Data Index: 410787 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.5567. Min Act: -0.0001

Data Index: 1414003 (Python Code)

Max Activating Token Index: 293

Text #17

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.5136. Min Act: -0.0001

Data Index: 795932 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.4793. Min Act: -0.0001

Data Index: 1586610 (Python Code)

Max Activating Token Index: 776

Text #19

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.5258. Min Act: -0.0001

Data Index: 476440 (C4 (Web Text))

Max Activating Token Index: 315