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

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

Neuron 494 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0506. Min Act: -0.0002

Data Index: 743538 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0506. Min Act: -0.0002

Data Index: 1268797 (C4 (Web Text))

Max Activating Token Index: 642

Text #2

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1199058 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0493. Min Act: -0.0002

Data Index: 939914 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0493. Min Act: -0.0002

Data Index: 1295920 (C4 (Web Text))

Max Activating Token Index: 477

Text #5

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0483. Min Act: -0.0002

Data Index: 1295146 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0474. Min Act: -0.0002

Data Index: 325672 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0442. Min Act: -0.0002

Data Index: 1019806 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0438. Min Act: -0.0002

Data Index: 1306404 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0408. Min Act: -0.0002

Data Index: 399036 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0443. Min Act: -0.0002

Data Index: 1060587 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1340787 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0419. Min Act: -0.0002

Data Index: 191050 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1193827 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0429. Min Act: -0.0002

Data Index: 716685 (C4 (Web Text))

Max Activating Token Index: 761

Text #15

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0427. Min Act: -0.0002

Data Index: 307020 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0449. Min Act: -0.0002

Data Index: 144760 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0409. Min Act: -0.0002

Data Index: 740533 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0438. Min Act: -0.0002

Data Index: 568220 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 0.0506. Min Range: -0.0506

Max Act: 0.0438. Min Act: -0.0002

Data Index: 512235 (C4 (Web Text))

Max Activating Token Index: 752