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

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

Neuron 3413 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2732. Min Range: -3.2732

Max Act: 3.2732. Min Act: -0.0000

Data Index: 316287 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 3.2732. Min Range: -3.2732

Max Act: 2.9896. Min Act: -0.0000

Data Index: 1274869 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 3.2732. Min Range: -3.2732

Max Act: 2.8430. Min Act: -0.0000

Data Index: 583721 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 3.2732. Min Range: -3.2732

Max Act: 2.7878. Min Act: -0.0000

Data Index: 967924 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 3.2732. Min Range: -3.2732

Max Act: 2.5810. Min Act: -0.0000

Data Index: 488052 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 3.2732. Min Range: -3.2732

Max Act: 2.7213. Min Act: -0.0000

Data Index: 187184 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 3.2732. Min Range: -3.2732

Max Act: 2.7117. Min Act: -0.0000

Data Index: 1596596 (Python Code)

Max Activating Token Index: 387

Text #7

Max Range: 3.2732. Min Range: -3.2732

Max Act: 2.7006. Min Act: -0.0000

Data Index: 970203 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 3.2732. Min Range: -3.2732

Max Act: 2.8370. Min Act: -0.0000

Data Index: 523379 (C4 (Web Text))

Max Activating Token Index: 995

Text #9

Max Range: 3.2732. Min Range: -3.2732

Max Act: 2.5382. Min Act: -0.0000

Data Index: 1081393 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 3.2732. Min Range: -3.2732

Max Act: 2.5532. Min Act: -0.0000

Data Index: 1173591 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 3.2732. Min Range: -3.2732

Max Act: 2.5388. Min Act: -0.0000

Data Index: 491308 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 3.2732. Min Range: -3.2732

Max Act: 2.4251. Min Act: -0.0000

Data Index: 459037 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 3.2732. Min Range: -3.2732

Max Act: 2.5014. Min Act: -0.0000

Data Index: 815388 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 3.2732. Min Range: -3.2732

Max Act: 2.4891. Min Act: -0.0000

Data Index: 1529122 (Python Code)

Max Activating Token Index: 737

Text #15

Max Range: 3.2732. Min Range: -3.2732

Max Act: 2.4329. Min Act: -0.0000

Data Index: 157456 (C4 (Web Text))

Max Activating Token Index: 989

Text #16

Max Range: 3.2732. Min Range: -3.2732

Max Act: 2.4351. Min Act: -0.0000

Data Index: 1381130 (Python Code)

Max Activating Token Index: 240

Text #17

Max Range: 3.2732. Min Range: -3.2732

Max Act: 2.2830. Min Act: -0.0000

Data Index: 326669 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 3.2732. Min Range: -3.2732

Max Act: 2.3922. Min Act: -0.0000

Data Index: 1307666 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 3.2732. Min Range: -3.2732

Max Act: 2.3824. Min Act: -0.0000

Data Index: 467588 (C4 (Web Text))

Max Activating Token Index: 662