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

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

Neuron 1739 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: 0.1340. Min Range: -0.1340

Max Act: 0.1340. Min Act: -0.0001

Data Index: 58387 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1273. Min Act: -0.0001

Data Index: 176037 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1258. Min Act: -0.0001

Data Index: 863112 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1221. Min Act: -0.0001

Data Index: 1147105 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1179. Min Act: -0.0001

Data Index: 215509 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1132. Min Act: -0.0001

Data Index: 1042956 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1085. Min Act: -0.0001

Data Index: 31558 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1170. Min Act: -0.0001

Data Index: 357998 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1155. Min Act: -0.0001

Data Index: 754060 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1131. Min Act: -0.0001

Data Index: 873005 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1060. Min Act: -0.0001

Data Index: 972819 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0977. Min Act: -0.0001

Data Index: 940452 (C4 (Web Text))

Max Activating Token Index: 712

Text #12

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1124. Min Act: -0.0001

Data Index: 5379 (C4 (Web Text))

Max Activating Token Index: 394

Text #13

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1158. Min Act: -0.0001

Data Index: 513137 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1091. Min Act: -0.0001

Data Index: 1078134 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1097. Min Act: -0.0001

Data Index: 228255 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1094. Min Act: -0.0001

Data Index: 1113509 (C4 (Web Text))

Max Activating Token Index: 258

Text #17

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1088. Min Act: -0.0001

Data Index: 1104161 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1119. Min Act: -0.0001

Data Index: 781327 (C4 (Web Text))

Max Activating Token Index: 407

Text #19

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1166. Min Act: -0.0001

Data Index: 437058 (C4 (Web Text))

Max Activating Token Index: 703