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

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

Neuron 3908 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3391. Min Range: -3.3391

Max Act: 3.3391. Min Act: -0.0000

Data Index: 1425295 (Python Code)

Max Activating Token Index: 947

Text #1

Max Range: 3.3391. Min Range: -3.3391

Max Act: 3.3109. Min Act: -0.0000

Data Index: 1567571 (Python Code)

Max Activating Token Index: 863

Text #2

Max Range: 3.3391. Min Range: -3.3391

Max Act: 2.8266. Min Act: -0.0000

Data Index: 1438873 (Python Code)

Max Activating Token Index: 686

Text #3

Max Range: 3.3391. Min Range: -3.3391

Max Act: 2.6191. Min Act: -0.0000

Data Index: 1366122 (Python Code)

Max Activating Token Index: 976

Text #4

Max Range: 3.3391. Min Range: -3.3391

Max Act: 2.7941. Min Act: -0.0000

Data Index: 1421981 (Python Code)

Max Activating Token Index: 266

Text #5

Max Range: 3.3391. Min Range: -3.3391

Max Act: 2.4792. Min Act: -0.0000

Data Index: 1558051 (Python Code)

Max Activating Token Index: 141

Text #6

Max Range: 3.3391. Min Range: -3.3391

Max Act: 2.5749. Min Act: -0.0000

Data Index: 1655290 (Python Code)

Max Activating Token Index: 310

Text #7

Max Range: 3.3391. Min Range: -3.3391

Max Act: 2.6669. Min Act: -0.0000

Data Index: 1568868 (Python Code)

Max Activating Token Index: 860

Text #8

Max Range: 3.3391. Min Range: -3.3391

Max Act: 2.5120. Min Act: -0.0000

Data Index: 1600529 (Python Code)

Max Activating Token Index: 542

Text #9

Max Range: 3.3391. Min Range: -3.3391

Max Act: 2.5032. Min Act: -0.0000

Data Index: 1568208 (Python Code)

Max Activating Token Index: 757

Text #10

Max Range: 3.3391. Min Range: -3.3391

Max Act: 2.3676. Min Act: -0.0000

Data Index: 1577237 (Python Code)

Max Activating Token Index: 563

Text #11

Max Range: 3.3391. Min Range: -3.3391

Max Act: 2.3725. Min Act: -0.0000

Data Index: 1636021 (Python Code)

Max Activating Token Index: 138

Text #12

Max Range: 3.3391. Min Range: -3.3391

Max Act: 2.4267. Min Act: -0.0000

Data Index: 1499290 (Python Code)

Max Activating Token Index: 722

Text #13

Max Range: 3.3391. Min Range: -3.3391

Max Act: 2.4212. Min Act: -0.0000

Data Index: 1656178 (Python Code)

Max Activating Token Index: 398

Text #14

Max Range: 3.3391. Min Range: -3.3391

Max Act: 2.4130. Min Act: -0.0000

Data Index: 1578815 (Python Code)

Max Activating Token Index: 218

Text #15

Max Range: 3.3391. Min Range: -3.3391

Max Act: 2.4160. Min Act: -0.0000

Data Index: 1491581 (Python Code)

Max Activating Token Index: 940

Text #16

Max Range: 3.3391. Min Range: -3.3391

Max Act: 2.5141. Min Act: -0.0000

Data Index: 1396057 (Python Code)

Max Activating Token Index: 862

Text #17

Max Range: 3.3391. Min Range: -3.3391

Max Act: 2.2804. Min Act: -0.0000

Data Index: 1491425 (Python Code)

Max Activating Token Index: 382

Text #18

Max Range: 3.3391. Min Range: -3.3391

Max Act: 2.3834. Min Act: -0.0000

Data Index: 1442921 (Python Code)

Max Activating Token Index: 932

Text #19

Max Range: 3.3391. Min Range: -3.3391

Max Act: 2.3402. Min Act: -0.0000

Data Index: 1613680 (Python Code)

Max Activating Token Index: 894