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

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

Neuron 499 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: 1.5733. Min Range: -1.5733

Max Act: 1.5733. Min Act: -0.0000

Data Index: 670277 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.2143. Min Act: -0.0000

Data Index: 1639420 (Python Code)

Max Activating Token Index: 891

Text #2

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.1948. Min Act: -0.0000

Data Index: 1212286 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.1110. Min Act: -0.0000

Data Index: 304818 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.1408. Min Act: -0.0000

Data Index: 1246789 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.0722. Min Act: -0.0000

Data Index: 524063 (C4 (Web Text))

Max Activating Token Index: 714

Text #6

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.0647. Min Act: -0.0000

Data Index: 320064 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.0055. Min Act: -0.0000

Data Index: 1126688 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.0318. Min Act: -0.0000

Data Index: 819076 (C4 (Web Text))

Max Activating Token Index: 917

Text #9

Max Range: 1.5733. Min Range: -1.5733

Max Act: 0.8779. Min Act: -0.0000

Data Index: 204781 (C4 (Web Text))

Max Activating Token Index: 129

Text #10

Max Range: 1.5733. Min Range: -1.5733

Max Act: 0.9900. Min Act: -0.0000

Data Index: 521338 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 1.5733. Min Range: -1.5733

Max Act: 0.9912. Min Act: -0.0000

Data Index: 360547 (C4 (Web Text))

Max Activating Token Index: 583

Text #12

Max Range: 1.5733. Min Range: -1.5733

Max Act: 0.9248. Min Act: -0.0000

Data Index: 680846 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 1.5733. Min Range: -1.5733

Max Act: 0.9450. Min Act: -0.0000

Data Index: 1239841 (C4 (Web Text))

Max Activating Token Index: 202

Text #14

Max Range: 1.5733. Min Range: -1.5733

Max Act: 1.0022. Min Act: -0.0000

Data Index: 1284757 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 1.5733. Min Range: -1.5733

Max Act: 0.9040. Min Act: -0.0000

Data Index: 1288342 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 1.5733. Min Range: -1.5733

Max Act: 0.8976. Min Act: -0.0000

Data Index: 841861 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 1.5733. Min Range: -1.5733

Max Act: 0.8760. Min Act: -0.0000

Data Index: 1516984 (Python Code)

Max Activating Token Index: 1006

Text #18

Max Range: 1.5733. Min Range: -1.5733

Max Act: 0.8842. Min Act: -0.0000

Data Index: 1144333 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 1.5733. Min Range: -1.5733

Max Act: 0.8577. Min Act: -0.0000

Data Index: 655274 (C4 (Web Text))

Max Activating Token Index: 311