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

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

Neuron 368 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.6601. Min Act: -0.0000

Data Index: 987854 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.6698. Min Act: -0.0000

Data Index: 532070 (C4 (Web Text))

Max Activating Token Index: 337

Text #2

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.7061. Min Act: -0.0000

Data Index: 64084 (C4 (Web Text))

Max Activating Token Index: 470

Text #3

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.6758. Min Act: -0.0000

Data Index: 904665 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.6728. Min Act: -0.0000

Data Index: 1325528 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.6691. Min Act: -0.0000

Data Index: 73818 (C4 (Web Text))

Max Activating Token Index: 311

Text #6

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.6401. Min Act: -0.0000

Data Index: 756372 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.6380. Min Act: -0.0000

Data Index: 472196 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.6551. Min Act: -0.0000

Data Index: 1292922 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.6664. Min Act: -0.0000

Data Index: 1484152 (Python Code)

Max Activating Token Index: 756

Text #10

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.6329. Min Act: -0.0000

Data Index: 891982 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.6368. Min Act: -0.0000

Data Index: 1356891 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.6240. Min Act: -0.0000

Data Index: 826725 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.6168. Min Act: -0.0000

Data Index: 821005 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.6149. Min Act: -0.0000

Data Index: 851273 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.5859. Min Act: -0.0000

Data Index: 350050 (C4 (Web Text))

Max Activating Token Index: 948

Text #16

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.6052. Min Act: -0.0000

Data Index: 857632 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.5661. Min Act: -0.0000

Data Index: 906366 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.5974. Min Act: -0.0000

Data Index: 811601 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.5928. Min Act: -0.0000

Data Index: 1648377 (Python Code)

Max Activating Token Index: 30