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

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

Neuron 2221 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.8995. Min Act: -0.0000

Data Index: 568283 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.9156. Min Act: -0.0000

Data Index: 1221763 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.9647. Min Act: 0.0000

Data Index: 503188 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.7991. Min Act: -0.0000

Data Index: 361739 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.7492. Min Act: -0.0000

Data Index: 1510773 (Python Code)

Max Activating Token Index: 7

Text #5

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.7492. Min Act: -0.0000

Data Index: 1456246 (Python Code)

Max Activating Token Index: 7

Text #6

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.6940. Min Act: -0.0000

Data Index: 976475 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.6893. Min Act: -0.0000

Data Index: 686095 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.7097. Min Act: -0.0000

Data Index: 1574047 (Python Code)

Max Activating Token Index: 267

Text #9

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.7208. Min Act: -0.0000

Data Index: 1291777 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.6677. Min Act: -0.0000

Data Index: 1618657 (Python Code)

Max Activating Token Index: 1001

Text #11

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.6776. Min Act: -0.0000

Data Index: 1511611 (Python Code)

Max Activating Token Index: 6

Text #12

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.6776. Min Act: -0.0000

Data Index: 1565924 (Python Code)

Max Activating Token Index: 6

Text #13

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.6776. Min Act: -0.0000

Data Index: 1559387 (Python Code)

Max Activating Token Index: 6

Text #14

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.6776. Min Act: -0.0000

Data Index: 1618747 (Python Code)

Max Activating Token Index: 6

Text #15

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.6776. Min Act: -0.0000

Data Index: 1425226 (Python Code)

Max Activating Token Index: 6

Text #16

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.6776. Min Act: -0.0000

Data Index: 1443893 (Python Code)

Max Activating Token Index: 6

Text #17

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.6776. Min Act: -0.0000

Data Index: 1501702 (Python Code)

Max Activating Token Index: 6

Text #18

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.6776. Min Act: -0.0000

Data Index: 1521023 (Python Code)

Max Activating Token Index: 6

Text #19

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.6818. Min Act: -0.0000

Data Index: 1554387 (Python Code)

Max Activating Token Index: 223