Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4029 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1819. Min Act: -0.0001

Data Index: 98859 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1634. Min Act: -0.0001

Data Index: 1235400 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1413. Min Act: -0.0001

Data Index: 1205985 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1414. Min Act: -0.0001

Data Index: 1161215 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1253. Min Act: -0.0001

Data Index: 1151862 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1117. Min Act: -0.0001

Data Index: 296960 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1154. Min Act: -0.0001

Data Index: 574923 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1070. Min Act: -0.0001

Data Index: 1257611 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1070. Min Act: -0.0001

Data Index: 258539 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1033. Min Act: -0.0001

Data Index: 1296416 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1062. Min Act: -0.0001

Data Index: 603623 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.0979. Min Act: -0.0001

Data Index: 1053390 (C4 (Web Text))

Max Activating Token Index: 693

Text #12

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1054. Min Act: -0.0001

Data Index: 477767 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.0970. Min Act: -0.0001

Data Index: 647841 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1007. Min Act: -0.0001

Data Index: 46702 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1096. Min Act: -0.0001

Data Index: 57997 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1015. Min Act: -0.0001

Data Index: 239894 (C4 (Web Text))

Max Activating Token Index: 639

Text #17

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1021. Min Act: -0.0001

Data Index: 1337493 (C4 (Web Text))

Max Activating Token Index: 473

Text #18

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.0986. Min Act: -0.0001

Data Index: 28479 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.0975. Min Act: -0.0001

Data Index: 416593 (C4 (Web Text))

Max Activating Token Index: 84