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

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

Neuron 5078 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.8864. Min Act: -0.0000

Data Index: 660140 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 1.0445. Min Range: -1.0445

Max Act: 1.0445. Min Act: -0.0000

Data Index: 1228768 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.9057. Min Act: -0.0000

Data Index: 1223564 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.8762. Min Act: -0.0000

Data Index: 380687 (C4 (Web Text))

Max Activating Token Index: 460

Text #4

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.8494. Min Act: -0.0000

Data Index: 337862 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.7809. Min Act: -0.0000

Data Index: 702210 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.7929. Min Act: -0.0000

Data Index: 1225053 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.7785. Min Act: -0.0000

Data Index: 552109 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.8187. Min Act: -0.0000

Data Index: 1274334 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.7666. Min Act: -0.0000

Data Index: 654602 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.7287. Min Act: -0.0000

Data Index: 654506 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.6803. Min Act: -0.0000

Data Index: 962874 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.7008. Min Act: -0.0000

Data Index: 189290 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.7002. Min Act: -0.0000

Data Index: 338791 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.6674. Min Act: -0.0000

Data Index: 96086 (C4 (Web Text))

Max Activating Token Index: 516

Text #15

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.5668. Min Act: -0.0000

Data Index: 674712 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.6393. Min Act: -0.0001

Data Index: 272779 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.6546. Min Act: -0.0000

Data Index: 626571 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.7005. Min Act: -0.0000

Data Index: 49817 (C4 (Web Text))

Max Activating Token Index: 711

Text #19

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.6534. Min Act: -0.0000

Data Index: 161876 (C4 (Web Text))

Max Activating Token Index: 41