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

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

Neuron 4396 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.4955. Min Act: -0.0000

Data Index: 311168 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.4725. Min Act: -0.0001

Data Index: 648848 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.4361. Min Act: -0.0001

Data Index: 1170901 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.4605. Min Act: -0.0001

Data Index: 268214 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.4035. Min Act: -0.0001

Data Index: 835239 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.3758. Min Act: -0.0001

Data Index: 103059 (C4 (Web Text))

Max Activating Token Index: 424

Text #6

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.4044. Min Act: -0.0001

Data Index: 1299866 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.3586. Min Act: -0.0001

Data Index: 398889 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.2505. Min Act: -0.0000

Data Index: 668554 (C4 (Web Text))

Max Activating Token Index: 988

Text #9

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.1765. Min Act: -0.0000

Data Index: 414510 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.1730. Min Act: -0.0001

Data Index: 659721 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.1649. Min Act: -0.0001

Data Index: 1110669 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.1797. Min Act: -0.0001

Data Index: 978253 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.1902. Min Act: -0.0001

Data Index: 12260 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.1761. Min Act: -0.0000

Data Index: 577402 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.1760. Min Act: -0.0000

Data Index: 139645 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.1575. Min Act: -0.0000

Data Index: 1254885 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.1591. Min Act: -0.0001

Data Index: 1147553 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.1696. Min Act: -0.0000

Data Index: 1042705 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.1991. Min Act: -0.0001

Data Index: 4647 (C4 (Web Text))

Max Activating Token Index: 273