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

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

Neuron 3237 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0550. Min Act: -0.0001

Data Index: 392938 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0453. Min Act: -0.0001

Data Index: 929869 (C4 (Web Text))

Max Activating Token Index: 766

Text #2

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0448. Min Act: -0.0001

Data Index: 7474 (C4 (Web Text))

Max Activating Token Index: 468

Text #3

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0389. Min Act: -0.0001

Data Index: 472639 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0413. Min Act: -0.0001

Data Index: 1276578 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0418. Min Act: -0.0001

Data Index: 787871 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0406. Min Act: -0.0001

Data Index: 768798 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0448. Min Act: -0.0001

Data Index: 458263 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0426. Min Act: -0.0001

Data Index: 816140 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0402. Min Act: -0.0001

Data Index: 1315183 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0392. Min Act: -0.0001

Data Index: 1160352 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0393. Min Act: -0.0001

Data Index: 1290522 (C4 (Web Text))

Max Activating Token Index: 321

Text #12

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0376. Min Act: -0.0001

Data Index: 448166 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0410. Min Act: -0.0001

Data Index: 957093 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0349. Min Act: -0.0001

Data Index: 791589 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0363. Min Act: -0.0001

Data Index: 166968 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0372. Min Act: -0.0001

Data Index: 62489 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0406. Min Act: -0.0001

Data Index: 641512 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0397. Min Act: -0.0001

Data Index: 944093 (C4 (Web Text))

Max Activating Token Index: 877

Text #19

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0368. Min Act: -0.0001

Data Index: 1340520 (C4 (Web Text))

Max Activating Token Index: 958