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

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

Neuron 386 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1888. Min Act: -0.0001

Data Index: 1191994 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1420. Min Act: -0.0001

Data Index: 405338 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1271. Min Act: -0.0001

Data Index: 202319 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1227. Min Act: -0.0001

Data Index: 443566 (C4 (Web Text))

Max Activating Token Index: 602

Text #4

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1062. Min Act: -0.0001

Data Index: 609587 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1119. Min Act: -0.0001

Data Index: 651236 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.0976. Min Act: -0.0001

Data Index: 1124663 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1046. Min Act: -0.0001

Data Index: 1294286 (C4 (Web Text))

Max Activating Token Index: 530

Text #8

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1022. Min Act: -0.0001

Data Index: 1206682 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1031. Min Act: -0.0001

Data Index: 1066684 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.0996. Min Act: -0.0001

Data Index: 21785 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.0934. Min Act: -0.0001

Data Index: 418845 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1010. Min Act: -0.0002

Data Index: 216899 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.0977. Min Act: -0.0001

Data Index: 583175 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.0955. Min Act: -0.0001

Data Index: 996591 (C4 (Web Text))

Max Activating Token Index: 995

Text #15

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.0944. Min Act: -0.0001

Data Index: 1173198 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.0899. Min Act: -0.0001

Data Index: 922146 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.0908. Min Act: -0.0001

Data Index: 661541 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.0860. Min Act: -0.0001

Data Index: 863121 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.0836. Min Act: -0.0001

Data Index: 821229 (C4 (Web Text))

Max Activating Token Index: 129