Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5000 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0495. Min Act: -0.0001

Data Index: 1197787 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0473. Min Act: -0.0001

Data Index: 1133101 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0436. Min Act: -0.0001

Data Index: 1242736 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0446. Min Act: -0.0001

Data Index: 87838 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0427. Min Act: -0.0001

Data Index: 668372 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0399. Min Act: -0.0001

Data Index: 466780 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0430. Min Act: -0.0001

Data Index: 613504 (C4 (Web Text))

Max Activating Token Index: 785

Text #7

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0417. Min Act: -0.0001

Data Index: 758716 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0393. Min Act: -0.0001

Data Index: 111833 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0403. Min Act: -0.0000

Data Index: 74782 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0370. Min Act: -0.0000

Data Index: 1301449 (C4 (Web Text))

Max Activating Token Index: 345

Text #11

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0383. Min Act: -0.0000

Data Index: 1313375 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0392. Min Act: -0.0001

Data Index: 602169 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0389. Min Act: -0.0001

Data Index: 690328 (C4 (Web Text))

Max Activating Token Index: 159

Text #14

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0326. Min Act: -0.0000

Data Index: 79497 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0344. Min Act: -0.0001

Data Index: 1249110 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0359. Min Act: -0.0000

Data Index: 530211 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0359. Min Act: -0.0000

Data Index: 79871 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0336. Min Act: -0.0001

Data Index: 1251740 (C4 (Web Text))

Max Activating Token Index: 491

Text #19

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0344. Min Act: -0.0001

Data Index: 414453 (C4 (Web Text))

Max Activating Token Index: 707