Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2451 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0437. Min Act: -0.0003

Data Index: 226717 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0427. Min Act: -0.0003

Data Index: 1268084 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0418. Min Act: -0.0003

Data Index: 840196 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0421. Min Act: -0.0003

Data Index: 1012324 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0421. Min Act: -0.0003

Data Index: 848803 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0440. Min Act: -0.0003

Data Index: 1051029 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0418. Min Act: -0.0003

Data Index: 300652 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0393. Min Act: -0.0003

Data Index: 1014713 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0401. Min Act: -0.0003

Data Index: 808018 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0393. Min Act: -0.0003

Data Index: 408265 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0389. Min Act: -0.0003

Data Index: 346859 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0381. Min Act: -0.0003

Data Index: 1210274 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0373. Min Act: -0.0003

Data Index: 1324384 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0372. Min Act: -0.0003

Data Index: 24219 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0363. Min Act: -0.0003

Data Index: 402436 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0358. Min Act: -0.0003

Data Index: 1297440 (C4 (Web Text))

Max Activating Token Index: 82

Text #16

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0357. Min Act: -0.0003

Data Index: 999834 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0371. Min Act: -0.0003

Data Index: 811677 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0376. Min Act: -0.0003

Data Index: 1284041 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0331. Min Act: -0.0003

Data Index: 307333 (C4 (Web Text))

Max Activating Token Index: 790