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

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

Neuron 730 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: 1.2574. Min Range: -1.2574

Max Act: 1.2574. Min Act: -0.0000

Data Index: 1237735 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 1.2574. Min Range: -1.2574

Max Act: 0.9623. Min Act: -0.0000

Data Index: 459732 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 1.2574. Min Range: -1.2574

Max Act: 0.6939. Min Act: -0.0000

Data Index: 672614 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 1.2574. Min Range: -1.2574

Max Act: 0.6816. Min Act: -0.0000

Data Index: 164947 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 1.2574. Min Range: -1.2574

Max Act: 0.5889. Min Act: -0.0000

Data Index: 78808 (C4 (Web Text))

Max Activating Token Index: 630

Text #5

Max Range: 1.2574. Min Range: -1.2574

Max Act: 0.6490. Min Act: -0.0000

Data Index: 319780 (C4 (Web Text))

Max Activating Token Index: 755

Text #6

Max Range: 1.2574. Min Range: -1.2574

Max Act: 0.6374. Min Act: -0.0000

Data Index: 1625547 (Python Code)

Max Activating Token Index: 55

Text #7

Max Range: 1.2574. Min Range: -1.2574

Max Act: 0.6555. Min Act: -0.0000

Data Index: 610315 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 1.2574. Min Range: -1.2574

Max Act: 0.5014. Min Act: -0.0000

Data Index: 579141 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 1.2574. Min Range: -1.2574

Max Act: 0.4818. Min Act: -0.0000

Data Index: 634237 (C4 (Web Text))

Max Activating Token Index: 630

Text #10

Max Range: 1.2574. Min Range: -1.2574

Max Act: 0.3616. Min Act: -0.0000

Data Index: 1646141 (Python Code)

Max Activating Token Index: 827

Text #11

Max Range: 1.2574. Min Range: -1.2574

Max Act: 0.4687. Min Act: -0.0000

Data Index: 113697 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 1.2574. Min Range: -1.2574

Max Act: 0.3621. Min Act: -0.0000

Data Index: 1444796 (Python Code)

Max Activating Token Index: 230

Text #13

Max Range: 1.2574. Min Range: -1.2574

Max Act: 0.4419. Min Act: -0.0000

Data Index: 326743 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 1.2574. Min Range: -1.2574

Max Act: 0.4508. Min Act: -0.0000

Data Index: 463887 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 1.2574. Min Range: -1.2574

Max Act: 0.4300. Min Act: -0.0000

Data Index: 808087 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 1.2574. Min Range: -1.2574

Max Act: 0.5142. Min Act: -0.0000

Data Index: 1235936 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 1.2574. Min Range: -1.2574

Max Act: 0.4450. Min Act: -0.0000

Data Index: 833769 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 1.2574. Min Range: -1.2574

Max Act: 0.4449. Min Act: -0.0000

Data Index: 1029742 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 1.2574. Min Range: -1.2574

Max Act: 0.4228. Min Act: -0.0000

Data Index: 51284 (C4 (Web Text))

Max Activating Token Index: 665