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

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

Neuron 5338 in Layer 1

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: 0.6748. Min Range: -0.6748

Max Act: 0.6748. Min Act: -0.0002

Data Index: 1411246 (Python Code)

Max Activating Token Index: 764

Text #1

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.6683. Min Act: -0.0002

Data Index: 1496209 (Python Code)

Max Activating Token Index: 860

Text #2

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.6394. Min Act: -0.0002

Data Index: 1448933 (Python Code)

Max Activating Token Index: 803

Text #3

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.6246. Min Act: -0.0002

Data Index: 1405998 (Python Code)

Max Activating Token Index: 902

Text #4

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.6243. Min Act: -0.0002

Data Index: 1440170 (Python Code)

Max Activating Token Index: 181

Text #5

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.6250. Min Act: -0.0002

Data Index: 1618612 (Python Code)

Max Activating Token Index: 740

Text #6

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.6284. Min Act: -0.0002

Data Index: 1559436 (Python Code)

Max Activating Token Index: 777

Text #7

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.6066. Min Act: -0.0002

Data Index: 1443001 (Python Code)

Max Activating Token Index: 694

Text #8

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.6111. Min Act: -0.0002

Data Index: 1374570 (Python Code)

Max Activating Token Index: 984

Text #9

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.6214. Min Act: -0.0002

Data Index: 1450155 (Python Code)

Max Activating Token Index: 772

Text #10

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.6000. Min Act: -0.0002

Data Index: 1484982 (Python Code)

Max Activating Token Index: 479

Text #11

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.6016. Min Act: -0.0002

Data Index: 1517460 (Python Code)

Max Activating Token Index: 894

Text #12

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.6133. Min Act: -0.0002

Data Index: 1627057 (Python Code)

Max Activating Token Index: 842

Text #13

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.5955. Min Act: -0.0002

Data Index: 1447856 (Python Code)

Max Activating Token Index: 954

Text #14

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.6076. Min Act: -0.0002

Data Index: 1641267 (Python Code)

Max Activating Token Index: 492

Text #15

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.6041. Min Act: -0.0002

Data Index: 1544803 (Python Code)

Max Activating Token Index: 148

Text #16

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.6044. Min Act: -0.0002

Data Index: 1579198 (Python Code)

Max Activating Token Index: 863

Text #17

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.5979. Min Act: -0.0002

Data Index: 1461627 (Python Code)

Max Activating Token Index: 974

Text #18

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.5932. Min Act: -0.0002

Data Index: 1502000 (Python Code)

Max Activating Token Index: 975

Text #19

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.5803. Min Act: -0.0002

Data Index: 1648776 (Python Code)

Max Activating Token Index: 718