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

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

Neuron 5093 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: 0.0662. Min Range: -0.0662

Max Act: 0.0654. Min Act: -0.0001

Data Index: 246435 (C4 (Web Text))

Max Activating Token Index: 518

Text #1

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0662. Min Act: -0.0001

Data Index: 555671 (C4 (Web Text))

Max Activating Token Index: 703

Text #2

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0437. Min Act: -0.0001

Data Index: 1344894 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0324. Min Act: -0.0001

Data Index: 1653416 (Python Code)

Max Activating Token Index: 167

Text #4

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0409. Min Act: -0.0001

Data Index: 103809 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0408. Min Act: -0.0001

Data Index: 1502728 (Python Code)

Max Activating Token Index: 721

Text #6

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0379. Min Act: -0.0001

Data Index: 618411 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0351. Min Act: -0.0001

Data Index: 906241 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0355. Min Act: -0.0001

Data Index: 115616 (C4 (Web Text))

Max Activating Token Index: 555

Text #9

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0368. Min Act: -0.0001

Data Index: 1542665 (Python Code)

Max Activating Token Index: 921

Text #10

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0289. Min Act: -0.0001

Data Index: 1390343 (Python Code)

Max Activating Token Index: 145

Text #11

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0342. Min Act: -0.0001

Data Index: 1323336 (C4 (Web Text))

Max Activating Token Index: 926

Text #12

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0319. Min Act: -0.0001

Data Index: 335989 (C4 (Web Text))

Max Activating Token Index: 640

Text #13

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0288. Min Act: -0.0001

Data Index: 1604346 (Python Code)

Max Activating Token Index: 98

Text #14

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0323. Min Act: -0.0001

Data Index: 1466665 (Python Code)

Max Activating Token Index: 218

Text #15

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0284. Min Act: -0.0001

Data Index: 1020341 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0308. Min Act: -0.0001

Data Index: 447409 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0333. Min Act: -0.0001

Data Index: 1081563 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0281. Min Act: -0.0001

Data Index: 1621540 (Python Code)

Max Activating Token Index: 86

Text #19

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0317. Min Act: -0.0001

Data Index: 238881 (C4 (Web Text))

Max Activating Token Index: 311