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

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

Neuron 3482 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0552. Min Act: -0.0001

Data Index: 920711 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0506. Min Act: -0.0001

Data Index: 10930 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0504. Min Act: -0.0001

Data Index: 537041 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0490. Min Act: -0.0001

Data Index: 764631 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0501. Min Act: -0.0001

Data Index: 370954 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0458. Min Act: -0.0001

Data Index: 1273859 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0438. Min Act: -0.0001

Data Index: 489409 (C4 (Web Text))

Max Activating Token Index: 523

Text #7

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0438. Min Act: -0.0001

Data Index: 106990 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0480. Min Act: -0.0001

Data Index: 204693 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0481. Min Act: -0.0001

Data Index: 1194815 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0480. Min Act: -0.0001

Data Index: 758297 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0441. Min Act: -0.0001

Data Index: 751794 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0514. Min Act: -0.0001

Data Index: 1003807 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0419. Min Act: -0.0001

Data Index: 1213058 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0432. Min Act: -0.0001

Data Index: 689665 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0430. Min Act: -0.0001

Data Index: 560281 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0429. Min Act: -0.0001

Data Index: 1320606 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0444. Min Act: -0.0001

Data Index: 669291 (C4 (Web Text))

Max Activating Token Index: 387

Text #18

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0431. Min Act: -0.0001

Data Index: 372226 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0412. Min Act: -0.0001

Data Index: 664484 (C4 (Web Text))

Max Activating Token Index: 53