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

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

Neuron 1527 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0809. Min Range: -3.0809

Max Act: 2.9750. Min Act: -0.0000

Data Index: 1464180 (Python Code)

Max Activating Token Index: 263

Text #1

Max Range: 3.0809. Min Range: -3.0809

Max Act: 2.8903. Min Act: -0.0000

Data Index: 1543266 (Python Code)

Max Activating Token Index: 333

Text #2

Max Range: 3.0809. Min Range: -3.0809

Max Act: 3.0809. Min Act: -0.0000

Data Index: 1366926 (Python Code)

Max Activating Token Index: 272

Text #3

Max Range: 3.0809. Min Range: -3.0809

Max Act: 2.6719. Min Act: -0.0000

Data Index: 292573 (C4 (Web Text))

Max Activating Token Index: 983

Text #4

Max Range: 3.0809. Min Range: -3.0809

Max Act: 2.6029. Min Act: -0.0000

Data Index: 1406951 (Python Code)

Max Activating Token Index: 508

Text #5

Max Range: 3.0809. Min Range: -3.0809

Max Act: 2.4300. Min Act: -0.0000

Data Index: 1485987 (Python Code)

Max Activating Token Index: 674

Text #6

Max Range: 3.0809. Min Range: -3.0809

Max Act: 2.2971. Min Act: -0.0000

Data Index: 1515415 (Python Code)

Max Activating Token Index: 81

Text #7

Max Range: 3.0809. Min Range: -3.0809

Max Act: 2.3725. Min Act: 0.0000

Data Index: 255580 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 3.0809. Min Range: -3.0809

Max Act: 2.0404. Min Act: -0.0000

Data Index: 1473683 (Python Code)

Max Activating Token Index: 98

Text #9

Max Range: 3.0809. Min Range: -3.0809

Max Act: 2.4073. Min Act: -0.0000

Data Index: 1609293 (Python Code)

Max Activating Token Index: 361

Text #10

Max Range: 3.0809. Min Range: -3.0809

Max Act: 2.2771. Min Act: -0.0000

Data Index: 409456 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 3.0809. Min Range: -3.0809

Max Act: 2.2418. Min Act: -0.0000

Data Index: 267917 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 3.0809. Min Range: -3.0809

Max Act: 2.1199. Min Act: -0.0000

Data Index: 1629802 (Python Code)

Max Activating Token Index: 184

Text #13

Max Range: 3.0809. Min Range: -3.0809

Max Act: 2.1698. Min Act: -0.0000

Data Index: 894000 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 3.0809. Min Range: -3.0809

Max Act: 2.0417. Min Act: -0.0000

Data Index: 64107 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 3.0809. Min Range: -3.0809

Max Act: 2.0220. Min Act: -0.0000

Data Index: 1623892 (Python Code)

Max Activating Token Index: 701

Text #16

Max Range: 3.0809. Min Range: -3.0809

Max Act: 2.1133. Min Act: -0.0000

Data Index: 583642 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 3.0809. Min Range: -3.0809

Max Act: 2.0024. Min Act: -0.0000

Data Index: 1181006 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 3.0809. Min Range: -3.0809

Max Act: 2.3530. Min Act: -0.0000

Data Index: 1407407 (Python Code)

Max Activating Token Index: 967

Text #19

Max Range: 3.0809. Min Range: -3.0809

Max Act: 1.9814. Min Act: -0.0000

Data Index: 1638798 (Python Code)

Max Activating Token Index: 214