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

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

Neuron 1398 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9330. Min Range: -3.9330

Max Act: 3.9330. Min Act: -0.0000

Data Index: 52804 (C4 (Web Text))

Max Activating Token Index: 516

Text #1

Max Range: 3.9330. Min Range: -3.9330

Max Act: 3.5272. Min Act: -0.0000

Data Index: 1097803 (C4 (Web Text))

Max Activating Token Index: 775

Text #2

Max Range: 3.9330. Min Range: -3.9330

Max Act: 3.2732. Min Act: -0.0000

Data Index: 995501 (C4 (Web Text))

Max Activating Token Index: 1012

Text #3

Max Range: 3.9330. Min Range: -3.9330

Max Act: 3.2206. Min Act: -0.0000

Data Index: 616600 (C4 (Web Text))

Max Activating Token Index: 449

Text #4

Max Range: 3.9330. Min Range: -3.9330

Max Act: 3.0561. Min Act: -0.0000

Data Index: 567595 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 3.9330. Min Range: -3.9330

Max Act: 2.9629. Min Act: -0.0000

Data Index: 142024 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 3.9330. Min Range: -3.9330

Max Act: 3.1022. Min Act: -0.0000

Data Index: 564343 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 3.9330. Min Range: -3.9330

Max Act: 3.1998. Min Act: -0.0000

Data Index: 372507 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 3.9330. Min Range: -3.9330

Max Act: 2.9128. Min Act: -0.0000

Data Index: 175221 (C4 (Web Text))

Max Activating Token Index: 559

Text #9

Max Range: 3.9330. Min Range: -3.9330

Max Act: 3.0049. Min Act: -0.0000

Data Index: 688107 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 3.9330. Min Range: -3.9330

Max Act: 2.8501. Min Act: -0.0000

Data Index: 465560 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 3.9330. Min Range: -3.9330

Max Act: 2.9367. Min Act: -0.0000

Data Index: 852444 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 3.9330. Min Range: -3.9330

Max Act: 2.8981. Min Act: -0.0000

Data Index: 630679 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 3.9330. Min Range: -3.9330

Max Act: 2.7231. Min Act: -0.0000

Data Index: 837338 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 3.9330. Min Range: -3.9330

Max Act: 2.7282. Min Act: -0.0000

Data Index: 1354493 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 3.9330. Min Range: -3.9330

Max Act: 2.8311. Min Act: -0.0000

Data Index: 822254 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 3.9330. Min Range: -3.9330

Max Act: 2.9639. Min Act: -0.0000

Data Index: 1333919 (C4 (Web Text))

Max Activating Token Index: 575

Text #17

Max Range: 3.9330. Min Range: -3.9330

Max Act: 2.6789. Min Act: -0.0000

Data Index: 187935 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 3.9330. Min Range: -3.9330

Max Act: 2.8004. Min Act: -0.0000

Data Index: 847975 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 3.9330. Min Range: -3.9330

Max Act: 2.5613. Min Act: -0.0000

Data Index: 1326066 (C4 (Web Text))

Max Activating Token Index: 684