Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1440 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0137. Min Act: -0.0001

Data Index: 1566729 (Python Code)

Max Activating Token Index: 802

Text #1

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0133. Min Act: -0.0001

Data Index: 1395894 (Python Code)

Max Activating Token Index: 947

Text #2

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0130. Min Act: -0.0001

Data Index: 1426814 (Python Code)

Max Activating Token Index: 892

Text #3

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0131. Min Act: -0.0001

Data Index: 915796 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0127. Min Act: -0.0002

Data Index: 1585553 (Python Code)

Max Activating Token Index: 671

Text #5

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0126. Min Act: -0.0001

Data Index: 1557658 (Python Code)

Max Activating Token Index: 865

Text #6

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0126. Min Act: -0.0001

Data Index: 357600 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0125. Min Act: -0.0001

Data Index: 1496897 (Python Code)

Max Activating Token Index: 804

Text #8

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0125. Min Act: -0.0001

Data Index: 1076239 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0124. Min Act: -0.0001

Data Index: 1617721 (Python Code)

Max Activating Token Index: 926

Text #10

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0124. Min Act: -0.0001

Data Index: 1373166 (Python Code)

Max Activating Token Index: 974

Text #11

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0122. Min Act: -0.0001

Data Index: 1625090 (Python Code)

Max Activating Token Index: 703

Text #12

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0121. Min Act: -0.0001

Data Index: 1596423 (Python Code)

Max Activating Token Index: 986

Text #13

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0119. Min Act: -0.0001

Data Index: 267213 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0119. Min Act: -0.0001

Data Index: 344575 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0118. Min Act: -0.0002

Data Index: 1375247 (Python Code)

Max Activating Token Index: 935

Text #16

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0119. Min Act: -0.0001

Data Index: 1656213 (Python Code)

Max Activating Token Index: 941

Text #17

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0116. Min Act: -0.0001

Data Index: 656054 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0116. Min Act: -0.0001

Data Index: 1611778 (Python Code)

Max Activating Token Index: 661

Text #19

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0116. Min Act: -0.0001

Data Index: 1532479 (Python Code)

Max Activating Token Index: 1009