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

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

Neuron 1033 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0698. Min Act: -0.0000

Data Index: 1471927 (Python Code)

Max Activating Token Index: 99

Text #1

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0463. Min Act: -0.0000

Data Index: 247267 (C4 (Web Text))

Max Activating Token Index: 860

Text #2

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0428. Min Act: -0.0000

Data Index: 1459135 (Python Code)

Max Activating Token Index: 259

Text #3

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0366. Min Act: -0.0000

Data Index: 1411514 (Python Code)

Max Activating Token Index: 657

Text #4

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0376. Min Act: -0.0000

Data Index: 1378928 (Python Code)

Max Activating Token Index: 115

Text #5

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0376. Min Act: -0.0000

Data Index: 1418830 (Python Code)

Max Activating Token Index: 996

Text #6

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0345. Min Act: -0.0000

Data Index: 1645818 (Python Code)

Max Activating Token Index: 178

Text #7

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0345. Min Act: -0.0000

Data Index: 1392041 (Python Code)

Max Activating Token Index: 822

Text #8

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0358. Min Act: -0.0000

Data Index: 721933 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0378. Min Act: -0.0000

Data Index: 1506508 (Python Code)

Max Activating Token Index: 755

Text #10

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0303. Min Act: -0.0000

Data Index: 1386555 (Python Code)

Max Activating Token Index: 873

Text #11

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0333. Min Act: -0.0000

Data Index: 1531694 (Python Code)

Max Activating Token Index: 324

Text #12

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0328. Min Act: -0.0000

Data Index: 1537213 (Python Code)

Max Activating Token Index: 1008

Text #13

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0306. Min Act: -0.0000

Data Index: 860213 (C4 (Web Text))

Max Activating Token Index: 826

Text #14

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0316. Min Act: -0.0000

Data Index: 1403442 (Python Code)

Max Activating Token Index: 783

Text #15

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0340. Min Act: -0.0000

Data Index: 240725 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0322. Min Act: -0.0000

Data Index: 729008 (C4 (Web Text))

Max Activating Token Index: 941

Text #17

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0312. Min Act: -0.0000

Data Index: 1468245 (Python Code)

Max Activating Token Index: 544

Text #18

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0319. Min Act: -0.0000

Data Index: 1010515 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0337. Min Act: -0.0000

Data Index: 868713 (C4 (Web Text))

Max Activating Token Index: 705