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

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

Neuron 1621 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: 0.5891. Min Range: -0.5891

Max Act: 0.5891. Min Act: -0.0000

Data Index: 1015080 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.5803. Min Act: -0.0000

Data Index: 1157067 (C4 (Web Text))

Max Activating Token Index: 338

Text #2

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.5249. Min Act: -0.0000

Data Index: 97708 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.5364. Min Act: -0.0000

Data Index: 871350 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.3844. Min Act: -0.0000

Data Index: 512921 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4191. Min Act: -0.0000

Data Index: 34302 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.3860. Min Act: -0.0000

Data Index: 740505 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.3943. Min Act: -0.0000

Data Index: 9316 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.3866. Min Act: -0.0000

Data Index: 1456298 (Python Code)

Max Activating Token Index: 664

Text #9

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.3785. Min Act: -0.0000

Data Index: 1452772 (Python Code)

Max Activating Token Index: 855

Text #10

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.3475. Min Act: -0.0000

Data Index: 1420587 (Python Code)

Max Activating Token Index: 1018

Text #11

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.3616. Min Act: -0.0000

Data Index: 226192 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.3738. Min Act: -0.0000

Data Index: 1144777 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.3314. Min Act: -0.0000

Data Index: 1526288 (Python Code)

Max Activating Token Index: 334

Text #14

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.3370. Min Act: -0.0000

Data Index: 1651269 (Python Code)

Max Activating Token Index: 940

Text #15

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.3552. Min Act: -0.0000

Data Index: 1338905 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.2992. Min Act: -0.0000

Data Index: 1225371 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.3317. Min Act: -0.0000

Data Index: 948011 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.3219. Min Act: -0.0000

Data Index: 27450 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.3678. Min Act: -0.0000

Data Index: 307830 (C4 (Web Text))

Max Activating Token Index: 1013