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

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

Neuron 1645 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1627. Min Act: -0.0001

Data Index: 1284784 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1455. Min Act: -0.0000

Data Index: 1025306 (C4 (Web Text))

Max Activating Token Index: 337

Text #2

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1381. Min Act: -0.0001

Data Index: 191756 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1270. Min Act: -0.0000

Data Index: 336369 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1284. Min Act: -0.0000

Data Index: 1310214 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1193. Min Act: -0.0000

Data Index: 51551 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1189. Min Act: -0.0001

Data Index: 654040 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1072. Min Act: -0.0000

Data Index: 843868 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1130. Min Act: -0.0000

Data Index: 761174 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1125. Min Act: -0.0000

Data Index: 1134948 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1084. Min Act: -0.0000

Data Index: 189322 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1114. Min Act: -0.0000

Data Index: 255084 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1067. Min Act: -0.0001

Data Index: 623682 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1055. Min Act: -0.0001

Data Index: 112700 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1029. Min Act: -0.0000

Data Index: 159021 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1018. Min Act: -0.0000

Data Index: 105551 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1014. Min Act: -0.0000

Data Index: 1085201 (C4 (Web Text))

Max Activating Token Index: 308

Text #17

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1011. Min Act: -0.0000

Data Index: 808044 (C4 (Web Text))

Max Activating Token Index: 441

Text #18

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1010. Min Act: -0.0001

Data Index: 797170 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.0970. Min Act: -0.0000

Data Index: 1264825 (C4 (Web Text))

Max Activating Token Index: 884