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

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

Neuron 3702 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: 0.6603. Min Range: -0.6603

Max Act: 0.6603. Min Act: -0.0000

Data Index: 770668 (C4 (Web Text))

Max Activating Token Index: 355

Text #1

Max Range: 0.6603. Min Range: -0.6603

Max Act: 0.6188. Min Act: -0.0000

Data Index: 803567 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 0.6603. Min Range: -0.6603

Max Act: 0.5073. Min Act: -0.0000

Data Index: 1322460 (C4 (Web Text))

Max Activating Token Index: 762

Text #3

Max Range: 0.6603. Min Range: -0.6603

Max Act: 0.5528. Min Act: -0.0000

Data Index: 325604 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 0.6603. Min Range: -0.6603

Max Act: 0.5014. Min Act: -0.0000

Data Index: 798307 (C4 (Web Text))

Max Activating Token Index: 465

Text #5

Max Range: 0.6603. Min Range: -0.6603

Max Act: 0.4740. Min Act: -0.0000

Data Index: 759215 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 0.6603. Min Range: -0.6603

Max Act: 0.4812. Min Act: -0.0000

Data Index: 465286 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 0.6603. Min Range: -0.6603

Max Act: 0.4937. Min Act: -0.0000

Data Index: 17915 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 0.6603. Min Range: -0.6603

Max Act: 0.4307. Min Act: -0.0000

Data Index: 317157 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 0.6603. Min Range: -0.6603

Max Act: 0.4396. Min Act: -0.0000

Data Index: 365787 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 0.6603. Min Range: -0.6603

Max Act: 0.3938. Min Act: -0.0000

Data Index: 212551 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 0.6603. Min Range: -0.6603

Max Act: 0.3985. Min Act: -0.0000

Data Index: 616084 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 0.6603. Min Range: -0.6603

Max Act: 0.3587. Min Act: -0.0000

Data Index: 356060 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 0.6603. Min Range: -0.6603

Max Act: 0.3677. Min Act: -0.0000

Data Index: 1081779 (C4 (Web Text))

Max Activating Token Index: 336

Text #14

Max Range: 0.6603. Min Range: -0.6603

Max Act: 0.3371. Min Act: -0.0000

Data Index: 452868 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 0.6603. Min Range: -0.6603

Max Act: 0.3681. Min Act: -0.0000

Data Index: 682721 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 0.6603. Min Range: -0.6603

Max Act: 0.3246. Min Act: -0.0000

Data Index: 158375 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 0.6603. Min Range: -0.6603

Max Act: 0.3113. Min Act: -0.0000

Data Index: 689105 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 0.6603. Min Range: -0.6603

Max Act: 0.3140. Min Act: -0.0000

Data Index: 104570 (C4 (Web Text))

Max Activating Token Index: 436

Text #19

Max Range: 0.6603. Min Range: -0.6603

Max Act: 0.3067. Min Act: -0.0000

Data Index: 1181220 (C4 (Web Text))

Max Activating Token Index: 212