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

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

Neuron 1336 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1271. Min Act: -0.0001

Data Index: 1442623 (Python Code)

Max Activating Token Index: 165

Text #1

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1284. Min Act: -0.0001

Data Index: 1652071 (Python Code)

Max Activating Token Index: 297

Text #2

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1125. Min Act: -0.0001

Data Index: 476742 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1128. Min Act: -0.0001

Data Index: 1337797 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1130. Min Act: -0.0001

Data Index: 1082781 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1130. Min Act: -0.0001

Data Index: 153710 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1112. Min Act: -0.0001

Data Index: 1291807 (C4 (Web Text))

Max Activating Token Index: 495

Text #7

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1092. Min Act: -0.0001

Data Index: 34376 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1045. Min Act: -0.0001

Data Index: 1161696 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1093. Min Act: -0.0001

Data Index: 730568 (C4 (Web Text))

Max Activating Token Index: 904

Text #10

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0960. Min Act: -0.0001

Data Index: 778333 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1052. Min Act: -0.0001

Data Index: 1134603 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1065. Min Act: -0.0001

Data Index: 1122910 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1041. Min Act: -0.0001

Data Index: 1015090 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1113. Min Act: -0.0001

Data Index: 749049 (C4 (Web Text))

Max Activating Token Index: 720

Text #15

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1074. Min Act: -0.0001

Data Index: 1338234 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1032. Min Act: -0.0001

Data Index: 569467 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1070. Min Act: -0.0001

Data Index: 1399643 (Python Code)

Max Activating Token Index: 195

Text #18

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1065. Min Act: -0.0001

Data Index: 292223 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1064. Min Act: -0.0001

Data Index: 1045482 (C4 (Web Text))

Max Activating Token Index: 945