Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1638 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1730. Min Act: -0.0001

Data Index: 283149 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1312. Min Act: -0.0001

Data Index: 211538 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1216. Min Act: -0.0001

Data Index: 1055664 (C4 (Web Text))

Max Activating Token Index: 448

Text #3

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1219. Min Act: -0.0000

Data Index: 497772 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1181. Min Act: -0.0001

Data Index: 437422 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1156. Min Act: -0.0001

Data Index: 1159961 (C4 (Web Text))

Max Activating Token Index: 1011

Text #6

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1129. Min Act: -0.0001

Data Index: 113100 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1171. Min Act: -0.0001

Data Index: 305251 (C4 (Web Text))

Max Activating Token Index: 361

Text #8

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1184. Min Act: -0.0001

Data Index: 381211 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1187. Min Act: -0.0001

Data Index: 237899 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1171. Min Act: -0.0001

Data Index: 1147650 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1092. Min Act: -0.0001

Data Index: 914753 (C4 (Web Text))

Max Activating Token Index: 721

Text #12

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1127. Min Act: -0.0001

Data Index: 242818 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1116. Min Act: -0.0001

Data Index: 1123623 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1077. Min Act: -0.0001

Data Index: 279060 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1113. Min Act: -0.0001

Data Index: 54200 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1064. Min Act: -0.0001

Data Index: 755521 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1062. Min Act: -0.0001

Data Index: 20331 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1092. Min Act: 0.0000

Data Index: 434091 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1085. Min Act: -0.0001

Data Index: 226875 (C4 (Web Text))

Max Activating Token Index: 386