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

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

Neuron 4445 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: 0.3203. Min Range: -0.3203

Max Act: 0.3203. Min Act: -0.0000

Data Index: 838760 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 0.3203. Min Range: -0.3203

Max Act: 0.2883. Min Act: -0.0000

Data Index: 738608 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 0.3203. Min Range: -0.3203

Max Act: 0.2576. Min Act: -0.0000

Data Index: 404195 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 0.3203. Min Range: -0.3203

Max Act: 0.2433. Min Act: -0.0000

Data Index: 682342 (C4 (Web Text))

Max Activating Token Index: 470

Text #4

Max Range: 0.3203. Min Range: -0.3203

Max Act: 0.2410. Min Act: -0.0000

Data Index: 176110 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 0.3203. Min Range: -0.3203

Max Act: 0.2091. Min Act: -0.0000

Data Index: 1083903 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 0.3203. Min Range: -0.3203

Max Act: 0.2281. Min Act: -0.0000

Data Index: 1049054 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 0.3203. Min Range: -0.3203

Max Act: 0.2114. Min Act: -0.0000

Data Index: 914331 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 0.3203. Min Range: -0.3203

Max Act: 0.2131. Min Act: -0.0000

Data Index: 788738 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 0.3203. Min Range: -0.3203

Max Act: 0.2116. Min Act: -0.0000

Data Index: 992356 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 0.3203. Min Range: -0.3203

Max Act: 0.1966. Min Act: -0.0000

Data Index: 721234 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 0.3203. Min Range: -0.3203

Max Act: 0.1893. Min Act: -0.0000

Data Index: 1138136 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 0.3203. Min Range: -0.3203

Max Act: 0.1875. Min Act: -0.0000

Data Index: 166741 (C4 (Web Text))

Max Activating Token Index: 989

Text #13

Max Range: 0.3203. Min Range: -0.3203

Max Act: 0.1825. Min Act: -0.0000

Data Index: 1286234 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 0.3203. Min Range: -0.3203

Max Act: 0.1749. Min Act: -0.0000

Data Index: 365418 (C4 (Web Text))

Max Activating Token Index: 461

Text #15

Max Range: 0.3203. Min Range: -0.3203

Max Act: 0.1839. Min Act: -0.0000

Data Index: 852879 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 0.3203. Min Range: -0.3203

Max Act: 0.1763. Min Act: -0.0000

Data Index: 152070 (C4 (Web Text))

Max Activating Token Index: 192

Text #17

Max Range: 0.3203. Min Range: -0.3203

Max Act: 0.1686. Min Act: -0.0000

Data Index: 67999 (C4 (Web Text))

Max Activating Token Index: 326

Text #18

Max Range: 0.3203. Min Range: -0.3203

Max Act: 0.1757. Min Act: -0.0000

Data Index: 1630726 (Python Code)

Max Activating Token Index: 431

Text #19

Max Range: 0.3203. Min Range: -0.3203

Max Act: 0.1567. Min Act: -0.0000

Data Index: 943349 (C4 (Web Text))

Max Activating Token Index: 441