Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1125 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8811. Min Range: -0.8811

Max Act: 0.8811. Min Act: -0.0000

Data Index: 1177704 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 0.8811. Min Range: -0.8811

Max Act: 0.8588. Min Act: -0.0000

Data Index: 632741 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 0.8811. Min Range: -0.8811

Max Act: 0.8211. Min Act: -0.0001

Data Index: 1269740 (C4 (Web Text))

Max Activating Token Index: 831

Text #3

Max Range: 0.8811. Min Range: -0.8811

Max Act: 0.8172. Min Act: -0.0000

Data Index: 996782 (C4 (Web Text))

Max Activating Token Index: 585

Text #4

Max Range: 0.8811. Min Range: -0.8811

Max Act: 0.7453. Min Act: -0.0000

Data Index: 117726 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 0.8811. Min Range: -0.8811

Max Act: 0.7175. Min Act: -0.0000

Data Index: 1119510 (C4 (Web Text))

Max Activating Token Index: 616

Text #6

Max Range: 0.8811. Min Range: -0.8811

Max Act: 0.7828. Min Act: -0.0000

Data Index: 568286 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 0.8811. Min Range: -0.8811

Max Act: 0.7456. Min Act: -0.0001

Data Index: 349567 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.8811. Min Range: -0.8811

Max Act: 0.7317. Min Act: -0.0000

Data Index: 1046499 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 0.8811. Min Range: -0.8811

Max Act: 0.7093. Min Act: -0.0000

Data Index: 189691 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 0.8811. Min Range: -0.8811

Max Act: 0.7253. Min Act: -0.0000

Data Index: 591390 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 0.8811. Min Range: -0.8811

Max Act: 0.7433. Min Act: -0.0000

Data Index: 1267498 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 0.8811. Min Range: -0.8811

Max Act: 0.6870. Min Act: -0.0000

Data Index: 981708 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 0.8811. Min Range: -0.8811

Max Act: 0.6790. Min Act: -0.0000

Data Index: 406147 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 0.8811. Min Range: -0.8811

Max Act: 0.6712. Min Act: -0.0001

Data Index: 109732 (C4 (Web Text))

Max Activating Token Index: 565

Text #15

Max Range: 0.8811. Min Range: -0.8811

Max Act: 0.6605. Min Act: -0.0001

Data Index: 1148122 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 0.8811. Min Range: -0.8811

Max Act: 0.6374. Min Act: -0.0000

Data Index: 639516 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 0.8811. Min Range: -0.8811

Max Act: 0.6553. Min Act: -0.0000

Data Index: 95896 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 0.8811. Min Range: -0.8811

Max Act: 0.6523. Min Act: -0.0000

Data Index: 673276 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 0.8811. Min Range: -0.8811

Max Act: 0.6452. Min Act: -0.0000

Data Index: 603192 (C4 (Web Text))

Max Activating Token Index: 970