Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 980 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0505. Min Act: -0.0003

Data Index: 864156 (C4 (Web Text))

Max Activating Token Index: 926

Text #1

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0501. Min Act: -0.0003

Data Index: 933609 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0505. Min Act: -0.0003

Data Index: 129522 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0451. Min Act: -0.0003

Data Index: 674832 (C4 (Web Text))

Max Activating Token Index: 388

Text #4

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0450. Min Act: -0.0003

Data Index: 1238936 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0434. Min Act: -0.0003

Data Index: 40307 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0429. Min Act: -0.0003

Data Index: 950043 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0413. Min Act: -0.0000

Data Index: 999492 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0409. Min Act: -0.0000

Data Index: 314566 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0410. Min Act: -0.0001

Data Index: 1222362 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0404. Min Act: -0.0002

Data Index: 238366 (C4 (Web Text))

Max Activating Token Index: 581

Text #11

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0400. Min Act: -0.0002

Data Index: 7754 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0410. Min Act: -0.0003

Data Index: 279395 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0391. Min Act: -0.0002

Data Index: 1267965 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0402. Min Act: -0.0003

Data Index: 671711 (C4 (Web Text))

Max Activating Token Index: 662

Text #15

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0388. Min Act: -0.0003

Data Index: 382642 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0404. Min Act: -0.0003

Data Index: 1137778 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0388. Min Act: -0.0003

Data Index: 355287 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0388. Min Act: -0.0004

Data Index: 865181 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0387. Min Act: -0.0002

Data Index: 1234607 (C4 (Web Text))

Max Activating Token Index: 446