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

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

Neuron 3242 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3490. Min Act: -0.0000

Data Index: 1084954 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2864. Min Act: -0.0000

Data Index: 952841 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2645. Min Act: -0.0000

Data Index: 1015324 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2567. Min Act: -0.0000

Data Index: 1185986 (C4 (Web Text))

Max Activating Token Index: 890

Text #4

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2495. Min Act: -0.0000

Data Index: 1022092 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2237. Min Act: -0.0000

Data Index: 650245 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2341. Min Act: -0.0000

Data Index: 300378 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2135. Min Act: -0.0000

Data Index: 673110 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2011. Min Act: -0.0000

Data Index: 916163 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.1926. Min Act: -0.0000

Data Index: 1550670 (Python Code)

Max Activating Token Index: 362

Text #10

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2061. Min Act: -0.0000

Data Index: 1318287 (C4 (Web Text))

Max Activating Token Index: 548

Text #11

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.1825. Min Act: -0.0000

Data Index: 1495684 (Python Code)

Max Activating Token Index: 785

Text #12

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.1910. Min Act: -0.0000

Data Index: 1449857 (Python Code)

Max Activating Token Index: 991

Text #13

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2009. Min Act: -0.0000

Data Index: 1392951 (Python Code)

Max Activating Token Index: 611

Text #14

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.1747. Min Act: -0.0000

Data Index: 1438973 (Python Code)

Max Activating Token Index: 973

Text #15

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.1891. Min Act: -0.0000

Data Index: 1070521 (C4 (Web Text))

Max Activating Token Index: 937

Text #16

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.1795. Min Act: -0.0000

Data Index: 922214 (C4 (Web Text))

Max Activating Token Index: 549

Text #17

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.1842. Min Act: -0.0000

Data Index: 278442 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.1829. Min Act: -0.0000

Data Index: 659477 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.1800. Min Act: -0.0000

Data Index: 772287 (C4 (Web Text))

Max Activating Token Index: 40