Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 108 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.2400. Min Range: -3.2400

Max Act: 3.2400. Min Act: -0.0001

Data Index: 599006 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 3.2400. Min Range: -3.2400

Max Act: 2.4249. Min Act: -0.0001

Data Index: 124137 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 3.2400. Min Range: -3.2400

Max Act: 2.3243. Min Act: -0.0001

Data Index: 798062 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 3.2400. Min Range: -3.2400

Max Act: 2.1080. Min Act: -0.0001

Data Index: 984965 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 3.2400. Min Range: -3.2400

Max Act: 2.0470. Min Act: -0.0001

Data Index: 146254 (C4 (Web Text))

Max Activating Token Index: 465

Text #5

Max Range: 3.2400. Min Range: -3.2400

Max Act: 2.1723. Min Act: -0.0001

Data Index: 1190155 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 3.2400. Min Range: -3.2400

Max Act: 2.0273. Min Act: -0.0001

Data Index: 740444 (C4 (Web Text))

Max Activating Token Index: 101

Text #7

Max Range: 3.2400. Min Range: -3.2400

Max Act: 2.0670. Min Act: -0.0001

Data Index: 68531 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 3.2400. Min Range: -3.2400

Max Act: 2.1859. Min Act: -0.0001

Data Index: 865041 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 3.2400. Min Range: -3.2400

Max Act: 1.9633. Min Act: -0.0001

Data Index: 1206964 (C4 (Web Text))

Max Activating Token Index: 330

Text #10

Max Range: 3.2400. Min Range: -3.2400

Max Act: 1.9652. Min Act: -0.0001

Data Index: 954185 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 3.2400. Min Range: -3.2400

Max Act: 1.9571. Min Act: -0.0001

Data Index: 679235 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 3.2400. Min Range: -3.2400

Max Act: 2.0321. Min Act: -0.0001

Data Index: 101354 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 3.2400. Min Range: -3.2400

Max Act: 1.9344. Min Act: -0.0001

Data Index: 81955 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 3.2400. Min Range: -3.2400

Max Act: 1.9220. Min Act: -0.0001

Data Index: 550696 (C4 (Web Text))

Max Activating Token Index: 445

Text #15

Max Range: 3.2400. Min Range: -3.2400

Max Act: 1.9035. Min Act: -0.0001

Data Index: 576513 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 3.2400. Min Range: -3.2400

Max Act: 1.7753. Min Act: -0.0001

Data Index: 406408 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 3.2400. Min Range: -3.2400

Max Act: 1.7250. Min Act: -0.0001

Data Index: 1356107 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 3.2400. Min Range: -3.2400

Max Act: 1.6657. Min Act: -0.0001

Data Index: 568039 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 3.2400. Min Range: -3.2400

Max Act: 1.9470. Min Act: -0.0001

Data Index: 13444 (C4 (Web Text))

Max Activating Token Index: 78