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

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

Neuron 4835 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1068. Min Range: -1.1068

Max Act: 1.1068. Min Act: -0.0000

Data Index: 1535517 (Python Code)

Max Activating Token Index: 806

Text #1

Max Range: 1.1068. Min Range: -1.1068

Max Act: 1.0500. Min Act: -0.0001

Data Index: 1568466 (Python Code)

Max Activating Token Index: 510

Text #2

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.9656. Min Act: -0.0000

Data Index: 857617 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.8737. Min Act: -0.0001

Data Index: 1443185 (Python Code)

Max Activating Token Index: 130

Text #4

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.8744. Min Act: -0.0000

Data Index: 1280981 (C4 (Web Text))

Max Activating Token Index: 802

Text #5

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.8575. Min Act: -0.0001

Data Index: 1629812 (Python Code)

Max Activating Token Index: 197

Text #6

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.8573. Min Act: -0.0000

Data Index: 1488147 (Python Code)

Max Activating Token Index: 11

Text #7

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.8408. Min Act: -0.0000

Data Index: 673004 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.8560. Min Act: -0.0000

Data Index: 1376773 (Python Code)

Max Activating Token Index: 76

Text #9

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.8013. Min Act: -0.0001

Data Index: 1371419 (Python Code)

Max Activating Token Index: 52

Text #10

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.7805. Min Act: -0.0000

Data Index: 568073 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.7999. Min Act: -0.0001

Data Index: 1488999 (Python Code)

Max Activating Token Index: 242

Text #12

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.7210. Min Act: -0.0000

Data Index: 1394424 (Python Code)

Max Activating Token Index: 115

Text #13

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.7444. Min Act: -0.0001

Data Index: 1618087 (Python Code)

Max Activating Token Index: 272

Text #14

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.7142. Min Act: -0.0000

Data Index: 1607334 (Python Code)

Max Activating Token Index: 8

Text #15

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.7361. Min Act: -0.0001

Data Index: 1379648 (Python Code)

Max Activating Token Index: 49

Text #16

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.7093. Min Act: -0.0000

Data Index: 1623344 (Python Code)

Max Activating Token Index: 551

Text #17

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.7678. Min Act: -0.0001

Data Index: 1445925 (Python Code)

Max Activating Token Index: 210

Text #18

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.7205. Min Act: -0.0001

Data Index: 105208 (C4 (Web Text))

Max Activating Token Index: 678

Text #19

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.7407. Min Act: -0.0000

Data Index: 1512762 (Python Code)

Max Activating Token Index: 510