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

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

Neuron 4690 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.7071. Min Act: -0.0000

Data Index: 780880 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.6130. Min Act: -0.0000

Data Index: 952831 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5456. Min Act: -0.0000

Data Index: 875878 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5212. Min Act: -0.0000

Data Index: 483052 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.4941. Min Act: -0.0000

Data Index: 175461 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5106. Min Act: -0.0000

Data Index: 296079 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.4848. Min Act: -0.0000

Data Index: 975925 (C4 (Web Text))

Max Activating Token Index: 532

Text #7

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.4980. Min Act: -0.0000

Data Index: 156738 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.4756. Min Act: -0.0000

Data Index: 1223631 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.4663. Min Act: -0.0000

Data Index: 915039 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.4157. Min Act: -0.0000

Data Index: 552600 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.4029. Min Act: -0.0000

Data Index: 1212740 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.4353. Min Act: -0.0000

Data Index: 1137066 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.4312. Min Act: -0.0000

Data Index: 1356114 (C4 (Web Text))

Max Activating Token Index: 994

Text #14

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.4352. Min Act: -0.0000

Data Index: 773327 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.3974. Min Act: -0.0000

Data Index: 401830 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.4381. Min Act: -0.0000

Data Index: 1263646 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.3677. Min Act: -0.0000

Data Index: 53534 (C4 (Web Text))

Max Activating Token Index: 960

Text #18

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.4193. Min Act: -0.0000

Data Index: 1306127 (C4 (Web Text))

Max Activating Token Index: 731

Text #19

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.3632. Min Act: -0.0000

Data Index: 59274 (C4 (Web Text))

Max Activating Token Index: 315