Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2410 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1079. Min Act: -0.0001

Data Index: 541903 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1154. Min Act: -0.0001

Data Index: 346838 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1127. Min Act: -0.0001

Data Index: 806560 (C4 (Web Text))

Max Activating Token Index: 468

Text #3

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0940. Min Act: -0.0001

Data Index: 520780 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1031. Min Act: -0.0001

Data Index: 627092 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1151. Min Act: -0.0001

Data Index: 747697 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1007. Min Act: -0.0001

Data Index: 1236619 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0990. Min Act: -0.0001

Data Index: 954411 (C4 (Web Text))

Max Activating Token Index: 350

Text #8

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1067. Min Act: -0.0001

Data Index: 1174662 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1025. Min Act: -0.0001

Data Index: 524167 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1018. Min Act: -0.0001

Data Index: 801423 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0875. Min Act: -0.0001

Data Index: 607728 (C4 (Web Text))

Max Activating Token Index: 824

Text #12

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0931. Min Act: -0.0001

Data Index: 1063432 (C4 (Web Text))

Max Activating Token Index: 170

Text #13

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0883. Min Act: -0.0001

Data Index: 296716 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0832. Min Act: -0.0001

Data Index: 98384 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0794. Min Act: -0.0001

Data Index: 811214 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0983. Min Act: -0.0001

Data Index: 1473075 (Python Code)

Max Activating Token Index: 536

Text #17

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0848. Min Act: -0.0001

Data Index: 492390 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0869. Min Act: -0.0001

Data Index: 35716 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0895. Min Act: -0.0001

Data Index: 619788 (C4 (Web Text))

Max Activating Token Index: 661