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

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

Neuron 832 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9085. Min Range: -3.9085

Max Act: 3.9085. Min Act: -0.0001

Data Index: 1497318 (Python Code)

Max Activating Token Index: 417

Text #1

Max Range: 3.9085. Min Range: -3.9085

Max Act: 3.6064. Min Act: -0.0000

Data Index: 1565849 (Python Code)

Max Activating Token Index: 699

Text #2

Max Range: 3.9085. Min Range: -3.9085

Max Act: 3.5501. Min Act: -0.0000

Data Index: 1520959 (Python Code)

Max Activating Token Index: 832

Text #3

Max Range: 3.9085. Min Range: -3.9085

Max Act: 3.4713. Min Act: -0.0000

Data Index: 1587189 (Python Code)

Max Activating Token Index: 616

Text #4

Max Range: 3.9085. Min Range: -3.9085

Max Act: 3.5785. Min Act: -0.0000

Data Index: 1503660 (Python Code)

Max Activating Token Index: 648

Text #5

Max Range: 3.9085. Min Range: -3.9085

Max Act: 3.7328. Min Act: -0.0000

Data Index: 1620120 (Python Code)

Max Activating Token Index: 748

Text #6

Max Range: 3.9085. Min Range: -3.9085

Max Act: 3.4804. Min Act: -0.0000

Data Index: 1409620 (Python Code)

Max Activating Token Index: 415

Text #7

Max Range: 3.9085. Min Range: -3.9085

Max Act: 3.6187. Min Act: -0.0000

Data Index: 1476144 (Python Code)

Max Activating Token Index: 906

Text #8

Max Range: 3.9085. Min Range: -3.9085

Max Act: 3.4351. Min Act: -0.0000

Data Index: 1447284 (Python Code)

Max Activating Token Index: 28

Text #9

Max Range: 3.9085. Min Range: -3.9085

Max Act: 3.3718. Min Act: -0.0000

Data Index: 1430842 (Python Code)

Max Activating Token Index: 1021

Text #10

Max Range: 3.9085. Min Range: -3.9085

Max Act: 3.2857. Min Act: -0.0000

Data Index: 1504777 (Python Code)

Max Activating Token Index: 683

Text #11

Max Range: 3.9085. Min Range: -3.9085

Max Act: 3.0514. Min Act: -0.0000

Data Index: 1494270 (Python Code)

Max Activating Token Index: 247

Text #12

Max Range: 3.9085. Min Range: -3.9085

Max Act: 3.1775. Min Act: -0.0000

Data Index: 1406933 (Python Code)

Max Activating Token Index: 640

Text #13

Max Range: 3.9085. Min Range: -3.9085

Max Act: 3.1745. Min Act: -0.0000

Data Index: 1488007 (Python Code)

Max Activating Token Index: 394

Text #14

Max Range: 3.9085. Min Range: -3.9085

Max Act: 3.1463. Min Act: -0.0000

Data Index: 1452907 (Python Code)

Max Activating Token Index: 256

Text #15

Max Range: 3.9085. Min Range: -3.9085

Max Act: 3.0157. Min Act: -0.0000

Data Index: 1573510 (Python Code)

Max Activating Token Index: 995

Text #16

Max Range: 3.9085. Min Range: -3.9085

Max Act: 3.2910. Min Act: -0.0000

Data Index: 1569730 (Python Code)

Max Activating Token Index: 737

Text #17

Max Range: 3.9085. Min Range: -3.9085

Max Act: 2.9898. Min Act: -0.0000

Data Index: 1497344 (Python Code)

Max Activating Token Index: 197

Text #18

Max Range: 3.9085. Min Range: -3.9085

Max Act: 3.0808. Min Act: -0.0000

Data Index: 1627289 (Python Code)

Max Activating Token Index: 212

Text #19

Max Range: 3.9085. Min Range: -3.9085

Max Act: 3.1041. Min Act: -0.0000

Data Index: 1361015 (Python Code)

Max Activating Token Index: 154