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

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

Neuron 570 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: 2.4108. Min Range: -2.4108

Max Act: 2.4065. Min Act: -0.0000

Data Index: 796421 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 2.4108. Min Range: -2.4108

Max Act: 2.4071. Min Act: -0.0000

Data Index: 83239 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 2.4108. Min Range: -2.4108

Max Act: 2.4108. Min Act: -0.0000

Data Index: 61585 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 2.4108. Min Range: -2.4108

Max Act: 2.3732. Min Act: -0.0000

Data Index: 550981 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 2.4108. Min Range: -2.4108

Max Act: 2.3625. Min Act: -0.0000

Data Index: 354329 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 2.4108. Min Range: -2.4108

Max Act: 2.2329. Min Act: -0.0000

Data Index: 1170032 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 2.4108. Min Range: -2.4108

Max Act: 2.2119. Min Act: -0.0000

Data Index: 723984 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 2.4108. Min Range: -2.4108

Max Act: 2.2814. Min Act: -0.0000

Data Index: 86426 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 2.4108. Min Range: -2.4108

Max Act: 2.3889. Min Act: -0.0000

Data Index: 202629 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 2.4108. Min Range: -2.4108

Max Act: 2.1230. Min Act: -0.0000

Data Index: 1353811 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 2.4108. Min Range: -2.4108

Max Act: 2.0556. Min Act: -0.0000

Data Index: 954822 (C4 (Web Text))

Max Activating Token Index: 397

Text #11

Max Range: 2.4108. Min Range: -2.4108

Max Act: 2.2621. Min Act: -0.0000

Data Index: 1329333 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 2.4108. Min Range: -2.4108

Max Act: 2.0314. Min Act: -0.0000

Data Index: 137223 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 2.4108. Min Range: -2.4108

Max Act: 2.2348. Min Act: -0.0000

Data Index: 635655 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 2.4108. Min Range: -2.4108

Max Act: 2.1003. Min Act: -0.0000

Data Index: 445221 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 2.4108. Min Range: -2.4108

Max Act: 2.1159. Min Act: -0.0000

Data Index: 554325 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 2.4108. Min Range: -2.4108

Max Act: 1.9743. Min Act: -0.0000

Data Index: 1034932 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 2.4108. Min Range: -2.4108

Max Act: 2.0828. Min Act: -0.0000

Data Index: 729584 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 2.4108. Min Range: -2.4108

Max Act: 2.1640. Min Act: -0.0000

Data Index: 517932 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 2.4108. Min Range: -2.4108

Max Act: 2.0607. Min Act: -0.0000

Data Index: 342168 (C4 (Web Text))

Max Activating Token Index: 489