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

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

Neuron 4780 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: 1.5267. Min Range: -1.5267

Max Act: 1.5267. Min Act: -0.0000

Data Index: 403931 (C4 (Web Text))

Max Activating Token Index: 444

Text #1

Max Range: 1.5267. Min Range: -1.5267

Max Act: 1.2831. Min Act: -0.0000

Data Index: 629735 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 1.5267. Min Range: -1.5267

Max Act: 1.1303. Min Act: -0.0000

Data Index: 915533 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 1.5267. Min Range: -1.5267

Max Act: 1.0289. Min Act: -0.0000

Data Index: 1427379 (Python Code)

Max Activating Token Index: 692

Text #4

Max Range: 1.5267. Min Range: -1.5267

Max Act: 1.0266. Min Act: -0.0000

Data Index: 627979 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 1.5267. Min Range: -1.5267

Max Act: 0.9980. Min Act: -0.0000

Data Index: 1644119 (Python Code)

Max Activating Token Index: 340

Text #6

Max Range: 1.5267. Min Range: -1.5267

Max Act: 1.0250. Min Act: -0.0000

Data Index: 1130248 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 1.5267. Min Range: -1.5267

Max Act: 0.9891. Min Act: -0.0000

Data Index: 1468912 (Python Code)

Max Activating Token Index: 416

Text #8

Max Range: 1.5267. Min Range: -1.5267

Max Act: 1.0049. Min Act: -0.0000

Data Index: 1418971 (Python Code)

Max Activating Token Index: 616

Text #9

Max Range: 1.5267. Min Range: -1.5267

Max Act: 0.9601. Min Act: -0.0000

Data Index: 1618261 (Python Code)

Max Activating Token Index: 609

Text #10

Max Range: 1.5267. Min Range: -1.5267

Max Act: 0.9565. Min Act: -0.0000

Data Index: 1502804 (Python Code)

Max Activating Token Index: 653

Text #11

Max Range: 1.5267. Min Range: -1.5267

Max Act: 0.9544. Min Act: -0.0000

Data Index: 770011 (C4 (Web Text))

Max Activating Token Index: 644

Text #12

Max Range: 1.5267. Min Range: -1.5267

Max Act: 0.9831. Min Act: -0.0000

Data Index: 1640003 (Python Code)

Max Activating Token Index: 907

Text #13

Max Range: 1.5267. Min Range: -1.5267

Max Act: 0.9409. Min Act: -0.0000

Data Index: 1628261 (Python Code)

Max Activating Token Index: 751

Text #14

Max Range: 1.5267. Min Range: -1.5267

Max Act: 0.9695. Min Act: -0.0000

Data Index: 1582162 (Python Code)

Max Activating Token Index: 139

Text #15

Max Range: 1.5267. Min Range: -1.5267

Max Act: 0.9394. Min Act: -0.0000

Data Index: 1508439 (Python Code)

Max Activating Token Index: 801

Text #16

Max Range: 1.5267. Min Range: -1.5267

Max Act: 0.9373. Min Act: -0.0000

Data Index: 1461451 (Python Code)

Max Activating Token Index: 905

Text #17

Max Range: 1.5267. Min Range: -1.5267

Max Act: 0.9909. Min Act: -0.0000

Data Index: 1631117 (Python Code)

Max Activating Token Index: 785

Text #18

Max Range: 1.5267. Min Range: -1.5267

Max Act: 0.9252. Min Act: -0.0000

Data Index: 1598145 (Python Code)

Max Activating Token Index: 1015

Text #19

Max Range: 1.5267. Min Range: -1.5267

Max Act: 0.9219. Min Act: -0.0000

Data Index: 731089 (C4 (Web Text))

Max Activating Token Index: 278