Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 588 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1340. Min Act: -0.0002

Data Index: 658817 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1254. Min Act: -0.0002

Data Index: 40522 (C4 (Web Text))

Max Activating Token Index: 408

Text #2

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1197. Min Act: -0.0002

Data Index: 949198 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1185. Min Act: -0.0002

Data Index: 311294 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1166. Min Act: -0.0002

Data Index: 879024 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1123. Min Act: -0.0002

Data Index: 1198796 (C4 (Web Text))

Max Activating Token Index: 126

Text #6

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1164. Min Act: -0.0002

Data Index: 306136 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1157. Min Act: -0.0002

Data Index: 811365 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1149. Min Act: -0.0002

Data Index: 876982 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1149. Min Act: -0.0002

Data Index: 370795 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1134. Min Act: -0.0002

Data Index: 1012157 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1143. Min Act: -0.0001

Data Index: 498821 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1159. Min Act: -0.0002

Data Index: 612931 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1121. Min Act: -0.0000

Data Index: 1287787 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1164. Min Act: -0.0002

Data Index: 761568 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1161. Min Act: -0.0002

Data Index: 931285 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1135. Min Act: -0.0002

Data Index: 761401 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1124. Min Act: -0.0002

Data Index: 95105 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1138. Min Act: -0.0002

Data Index: 282333 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1119. Min Act: -0.0002

Data Index: 513883 (C4 (Web Text))

Max Activating Token Index: 250