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

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

Neuron 2365 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1548. Min Act: -0.0001

Data Index: 233841 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1328. Min Act: -0.0001

Data Index: 74926 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1323. Min Act: -0.0001

Data Index: 454543 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1358. Min Act: -0.0001

Data Index: 166180 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1281. Min Act: -0.0001

Data Index: 143922 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1173. Min Act: -0.0001

Data Index: 780615 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1256. Min Act: -0.0001

Data Index: 1225166 (C4 (Web Text))

Max Activating Token Index: 472

Text #7

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1197. Min Act: -0.0001

Data Index: 1244107 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1212. Min Act: -0.0001

Data Index: 405955 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1164. Min Act: -0.0001

Data Index: 692193 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1112. Min Act: -0.0001

Data Index: 1335867 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1159. Min Act: -0.0001

Data Index: 259839 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1109. Min Act: -0.0001

Data Index: 1136300 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1097. Min Act: -0.0001

Data Index: 503773 (C4 (Web Text))

Max Activating Token Index: 673

Text #14

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1189. Min Act: -0.0001

Data Index: 1349985 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1054. Min Act: -0.0001

Data Index: 695945 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1128. Min Act: -0.0001

Data Index: 324400 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1113. Min Act: -0.0001

Data Index: 1090284 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1069. Min Act: -0.0001

Data Index: 77865 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1100. Min Act: -0.0001

Data Index: 983619 (C4 (Web Text))

Max Activating Token Index: 969