Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 997 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0538. Min Act: -0.0006

Data Index: 783483 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0484. Min Act: -0.0006

Data Index: 654904 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0464. Min Act: -0.0006

Data Index: 247692 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0465. Min Act: -0.0006

Data Index: 366212 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0451. Min Act: -0.0006

Data Index: 391884 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0468. Min Act: -0.0006

Data Index: 170866 (C4 (Web Text))

Max Activating Token Index: 553

Text #6

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0467. Min Act: -0.0006

Data Index: 1106542 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0456. Min Act: -0.0006

Data Index: 1312893 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0450. Min Act: -0.0006

Data Index: 789680 (C4 (Web Text))

Max Activating Token Index: 567

Text #9

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0462. Min Act: -0.0006

Data Index: 314473 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0431. Min Act: -0.0006

Data Index: 55258 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0440. Min Act: -0.0006

Data Index: 96982 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0447. Min Act: -0.0006

Data Index: 1167518 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0444. Min Act: -0.0006

Data Index: 529323 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0436. Min Act: -0.0006

Data Index: 234128 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0424. Min Act: -0.0006

Data Index: 1060555 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0433. Min Act: -0.0006

Data Index: 315574 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0435. Min Act: -0.0006

Data Index: 979840 (C4 (Web Text))

Max Activating Token Index: 628

Text #18

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0431. Min Act: -0.0006

Data Index: 456785 (C4 (Web Text))

Max Activating Token Index: 568

Text #19

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0442. Min Act: -0.0006

Data Index: 732701 (C4 (Web Text))

Max Activating Token Index: 578