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

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

Neuron 4883 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2919. Min Range: -1.2919

Max Act: 1.2919. Min Act: -0.0000

Data Index: 1528962 (Python Code)

Max Activating Token Index: 87

Text #1

Max Range: 1.2919. Min Range: -1.2919

Max Act: 0.8983. Min Act: -0.0000

Data Index: 1362629 (Python Code)

Max Activating Token Index: 748

Text #2

Max Range: 1.2919. Min Range: -1.2919

Max Act: 0.9003. Min Act: -0.0000

Data Index: 941647 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 1.2919. Min Range: -1.2919

Max Act: 0.9041. Min Act: -0.0001

Data Index: 1272042 (C4 (Web Text))

Max Activating Token Index: 202

Text #4

Max Range: 1.2919. Min Range: -1.2919

Max Act: 0.8374. Min Act: -0.0000

Data Index: 1558261 (Python Code)

Max Activating Token Index: 709

Text #5

Max Range: 1.2919. Min Range: -1.2919

Max Act: 0.8032. Min Act: -0.0000

Data Index: 390959 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 1.2919. Min Range: -1.2919

Max Act: 0.7912. Min Act: -0.0000

Data Index: 1536180 (Python Code)

Max Activating Token Index: 33

Text #7

Max Range: 1.2919. Min Range: -1.2919

Max Act: 0.7361. Min Act: -0.0001

Data Index: 1331868 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 1.2919. Min Range: -1.2919

Max Act: 0.7536. Min Act: -0.0000

Data Index: 906783 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 1.2919. Min Range: -1.2919

Max Act: 0.7769. Min Act: -0.0001

Data Index: 1470826 (Python Code)

Max Activating Token Index: 894

Text #10

Max Range: 1.2919. Min Range: -1.2919

Max Act: 0.7503. Min Act: -0.0001

Data Index: 1637962 (Python Code)

Max Activating Token Index: 398

Text #11

Max Range: 1.2919. Min Range: -1.2919

Max Act: 0.7496. Min Act: -0.0001

Data Index: 1537735 (Python Code)

Max Activating Token Index: 1018

Text #12

Max Range: 1.2919. Min Range: -1.2919

Max Act: 0.7053. Min Act: -0.0000

Data Index: 1574529 (Python Code)

Max Activating Token Index: 1000

Text #13

Max Range: 1.2919. Min Range: -1.2919

Max Act: 0.6879. Min Act: -0.0001

Data Index: 1579184 (Python Code)

Max Activating Token Index: 119

Text #14

Max Range: 1.2919. Min Range: -1.2919

Max Act: 0.6673. Min Act: -0.0001

Data Index: 1433040 (Python Code)

Max Activating Token Index: 182

Text #15

Max Range: 1.2919. Min Range: -1.2919

Max Act: 0.6679. Min Act: -0.0001

Data Index: 1529294 (Python Code)

Max Activating Token Index: 309

Text #16

Max Range: 1.2919. Min Range: -1.2919

Max Act: 0.6711. Min Act: -0.0001

Data Index: 366161 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 1.2919. Min Range: -1.2919

Max Act: 0.6705. Min Act: -0.0001

Data Index: 574339 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 1.2919. Min Range: -1.2919

Max Act: 0.6434. Min Act: -0.0001

Data Index: 185432 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 1.2919. Min Range: -1.2919

Max Act: 0.5955. Min Act: -0.0001

Data Index: 1596136 (Python Code)

Max Activating Token Index: 177