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

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

Neuron 3742 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: 2.0633. Min Range: -2.0633

Max Act: 1.9315. Min Act: 0.0000

Data Index: 1037201 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 2.0633. Min Range: -2.0633

Max Act: 2.0633. Min Act: -0.0000

Data Index: 1255479 (C4 (Web Text))

Max Activating Token Index: 703

Text #2

Max Range: 2.0633. Min Range: -2.0633

Max Act: 1.6625. Min Act: -0.0000

Data Index: 209164 (C4 (Web Text))

Max Activating Token Index: 217

Text #3

Max Range: 2.0633. Min Range: -2.0633

Max Act: 1.5883. Min Act: -0.0000

Data Index: 460960 (C4 (Web Text))

Max Activating Token Index: 864

Text #4

Max Range: 2.0633. Min Range: -2.0633

Max Act: 1.5299. Min Act: -0.0000

Data Index: 789393 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 2.0633. Min Range: -2.0633

Max Act: 1.5030. Min Act: -0.0000

Data Index: 624806 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 2.0633. Min Range: -2.0633

Max Act: 1.4633. Min Act: -0.0000

Data Index: 901427 (C4 (Web Text))

Max Activating Token Index: 529

Text #7

Max Range: 2.0633. Min Range: -2.0633

Max Act: 1.3045. Min Act: -0.0000

Data Index: 1559402 (Python Code)

Max Activating Token Index: 597

Text #8

Max Range: 2.0633. Min Range: -2.0633

Max Act: 1.4990. Min Act: -0.0000

Data Index: 659991 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 2.0633. Min Range: -2.0633

Max Act: 1.4240. Min Act: -0.0000

Data Index: 1320405 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 2.0633. Min Range: -2.0633

Max Act: 1.4044. Min Act: -0.0000

Data Index: 214115 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 2.0633. Min Range: -2.0633

Max Act: 1.3986. Min Act: -0.0000

Data Index: 1287575 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 2.0633. Min Range: -2.0633

Max Act: 1.1621. Min Act: -0.0000

Data Index: 455472 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 2.0633. Min Range: -2.0633

Max Act: 1.4212. Min Act: -0.0000

Data Index: 1401766 (Python Code)

Max Activating Token Index: 224

Text #14

Max Range: 2.0633. Min Range: -2.0633

Max Act: 1.5046. Min Act: -0.0000

Data Index: 816972 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 2.0633. Min Range: -2.0633

Max Act: 1.4375. Min Act: -0.0000

Data Index: 143560 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 2.0633. Min Range: -2.0633

Max Act: 1.3342. Min Act: -0.0000

Data Index: 509623 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 2.0633. Min Range: -2.0633

Max Act: 1.3520. Min Act: -0.0000

Data Index: 560043 (C4 (Web Text))

Max Activating Token Index: 546

Text #18

Max Range: 2.0633. Min Range: -2.0633

Max Act: 1.3140. Min Act: -0.0000

Data Index: 369547 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 2.0633. Min Range: -2.0633

Max Act: 1.2302. Min Act: -0.0000

Data Index: 1409084 (Python Code)

Max Activating Token Index: 862