Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1542 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1172. Min Act: -0.0001

Data Index: 737890 (C4 (Web Text))

Max Activating Token Index: 217

Text #1

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1061. Min Act: -0.0001

Data Index: 35982 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1271. Min Act: -0.0001

Data Index: 146668 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1121. Min Act: -0.0001

Data Index: 527337 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1123. Min Act: -0.0001

Data Index: 584244 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1044. Min Act: -0.0001

Data Index: 1073757 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1081. Min Act: -0.0001

Data Index: 1285561 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1158. Min Act: -0.0001

Data Index: 758066 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1132. Min Act: -0.0001

Data Index: 1493262 (Python Code)

Max Activating Token Index: 746

Text #9

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1031. Min Act: -0.0001

Data Index: 646169 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.0995. Min Act: -0.0001

Data Index: 726558 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1003. Min Act: -0.0001

Data Index: 1570560 (Python Code)

Max Activating Token Index: 578

Text #12

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.0916. Min Act: -0.0001

Data Index: 796119 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1061. Min Act: -0.0001

Data Index: 568016 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.0984. Min Act: -0.0001

Data Index: 170356 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.0980. Min Act: -0.0001

Data Index: 1295519 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.0975. Min Act: -0.0001

Data Index: 1193494 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1001. Min Act: -0.0001

Data Index: 832341 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.0986. Min Act: -0.0001

Data Index: 1237974 (C4 (Web Text))

Max Activating Token Index: 331

Text #19

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.0815. Min Act: -0.0001

Data Index: 674033 (C4 (Web Text))

Max Activating Token Index: 197