Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 943 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0075. Min Act: -0.0006

Data Index: 1304389 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0061. Min Act: -0.0006

Data Index: 1485243 (Python Code)

Max Activating Token Index: 34

Text #2

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0058. Min Act: -0.0006

Data Index: 1648846 (Python Code)

Max Activating Token Index: 689

Text #3

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0053. Min Act: -0.0006

Data Index: 29505 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0055. Min Act: -0.0006

Data Index: 186288 (C4 (Web Text))

Max Activating Token Index: 836

Text #5

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0054. Min Act: -0.0006

Data Index: 1147860 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0053. Min Act: -0.0006

Data Index: 1600328 (Python Code)

Max Activating Token Index: 92

Text #7

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0052. Min Act: -0.0006

Data Index: 1400766 (Python Code)

Max Activating Token Index: 504

Text #8

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0053. Min Act: -0.0006

Data Index: 4478 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0051. Min Act: -0.0006

Data Index: 1630221 (Python Code)

Max Activating Token Index: 606

Text #10

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0049. Min Act: -0.0006

Data Index: 1397301 (Python Code)

Max Activating Token Index: 484

Text #11

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0051. Min Act: -0.0006

Data Index: 933832 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0050. Min Act: -0.0006

Data Index: 1489368 (Python Code)

Max Activating Token Index: 121

Text #13

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0051. Min Act: -0.0006

Data Index: 770459 (C4 (Web Text))

Max Activating Token Index: 998

Text #14

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0049. Min Act: -0.0006

Data Index: 839311 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0048. Min Act: -0.0006

Data Index: 496622 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0050. Min Act: -0.0006

Data Index: 153045 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0049. Min Act: -0.0006

Data Index: 690801 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0050. Min Act: -0.0006

Data Index: 1606231 (Python Code)

Max Activating Token Index: 105

Text #19

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0049. Min Act: -0.0006

Data Index: 288306 (C4 (Web Text))

Max Activating Token Index: 19