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

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

Neuron 5645 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: 2.2903. Min Range: -2.2903

Max Act: 2.2903. Min Act: -0.0000

Data Index: 352373 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 2.2903. Min Range: -2.2903

Max Act: 2.2377. Min Act: -0.0000

Data Index: 1303394 (C4 (Web Text))

Max Activating Token Index: 682

Text #2

Max Range: 2.2903. Min Range: -2.2903

Max Act: 2.0835. Min Act: -0.0000

Data Index: 558243 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 2.2903. Min Range: -2.2903

Max Act: 1.8219. Min Act: -0.0000

Data Index: 367813 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 2.2903. Min Range: -2.2903

Max Act: 1.8199. Min Act: -0.0000

Data Index: 401210 (C4 (Web Text))

Max Activating Token Index: 947

Text #5

Max Range: 2.2903. Min Range: -2.2903

Max Act: 1.7370. Min Act: -0.0000

Data Index: 1574464 (Python Code)

Max Activating Token Index: 1009

Text #6

Max Range: 2.2903. Min Range: -2.2903

Max Act: 2.0647. Min Act: -0.0000

Data Index: 314841 (C4 (Web Text))

Max Activating Token Index: 777

Text #7

Max Range: 2.2903. Min Range: -2.2903

Max Act: 1.6615. Min Act: -0.0000

Data Index: 1502140 (Python Code)

Max Activating Token Index: 639

Text #8

Max Range: 2.2903. Min Range: -2.2903

Max Act: 1.7089. Min Act: -0.0000

Data Index: 1547850 (Python Code)

Max Activating Token Index: 831

Text #9

Max Range: 2.2903. Min Range: -2.2903

Max Act: 1.5903. Min Act: -0.0000

Data Index: 871566 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 2.2903. Min Range: -2.2903

Max Act: 1.5660. Min Act: -0.0000

Data Index: 908836 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 2.2903. Min Range: -2.2903

Max Act: 1.6409. Min Act: -0.0000

Data Index: 335562 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 2.2903. Min Range: -2.2903

Max Act: 1.6437. Min Act: -0.0000

Data Index: 1440115 (Python Code)

Max Activating Token Index: 549

Text #13

Max Range: 2.2903. Min Range: -2.2903

Max Act: 1.5526. Min Act: -0.0000

Data Index: 1530160 (Python Code)

Max Activating Token Index: 1002

Text #14

Max Range: 2.2903. Min Range: -2.2903

Max Act: 1.7136. Min Act: -0.0000

Data Index: 434686 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 2.2903. Min Range: -2.2903

Max Act: 1.7057. Min Act: -0.0000

Data Index: 277507 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 2.2903. Min Range: -2.2903

Max Act: 1.6211. Min Act: -0.0000

Data Index: 1522504 (Python Code)

Max Activating Token Index: 981

Text #17

Max Range: 2.2903. Min Range: -2.2903

Max Act: 1.6006. Min Act: -0.0000

Data Index: 416848 (C4 (Web Text))

Max Activating Token Index: 467

Text #18

Max Range: 2.2903. Min Range: -2.2903

Max Act: 1.5966. Min Act: -0.0000

Data Index: 1567638 (Python Code)

Max Activating Token Index: 79

Text #19

Max Range: 2.2903. Min Range: -2.2903

Max Act: 1.8644. Min Act: -0.0000

Data Index: 1372270 (Python Code)

Max Activating Token Index: 160