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

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

Neuron 4107 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: 2.4235. Min Range: -2.4235

Max Act: 2.4235. Min Act: -0.0000

Data Index: 1363374 (Python Code)

Max Activating Token Index: 343

Text #1

Max Range: 2.4235. Min Range: -2.4235

Max Act: 2.2853. Min Act: -0.0000

Data Index: 1499329 (Python Code)

Max Activating Token Index: 301

Text #2

Max Range: 2.4235. Min Range: -2.4235

Max Act: 2.2562. Min Act: -0.0000

Data Index: 1455678 (Python Code)

Max Activating Token Index: 535

Text #3

Max Range: 2.4235. Min Range: -2.4235

Max Act: 2.3370. Min Act: -0.0000

Data Index: 1397755 (Python Code)

Max Activating Token Index: 683

Text #4

Max Range: 2.4235. Min Range: -2.4235

Max Act: 2.3527. Min Act: -0.0000

Data Index: 1531965 (Python Code)

Max Activating Token Index: 771

Text #5

Max Range: 2.4235. Min Range: -2.4235

Max Act: 2.3967. Min Act: -0.0000

Data Index: 1365555 (Python Code)

Max Activating Token Index: 578

Text #6

Max Range: 2.4235. Min Range: -2.4235

Max Act: 2.2601. Min Act: -0.0000

Data Index: 1636928 (Python Code)

Max Activating Token Index: 601

Text #7

Max Range: 2.4235. Min Range: -2.4235

Max Act: 2.0207. Min Act: -0.0000

Data Index: 1421797 (Python Code)

Max Activating Token Index: 669

Text #8

Max Range: 2.4235. Min Range: -2.4235

Max Act: 2.0693. Min Act: -0.0000

Data Index: 899128 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 2.4235. Min Range: -2.4235

Max Act: 2.1483. Min Act: -0.0000

Data Index: 1572114 (Python Code)

Max Activating Token Index: 181

Text #10

Max Range: 2.4235. Min Range: -2.4235

Max Act: 1.9112. Min Act: -0.0000

Data Index: 564299 (C4 (Web Text))

Max Activating Token Index: 492

Text #11

Max Range: 2.4235. Min Range: -2.4235

Max Act: 2.0060. Min Act: -0.0000

Data Index: 742362 (C4 (Web Text))

Max Activating Token Index: 464

Text #12

Max Range: 2.4235. Min Range: -2.4235

Max Act: 2.0625. Min Act: -0.0000

Data Index: 1387059 (Python Code)

Max Activating Token Index: 294

Text #13

Max Range: 2.4235. Min Range: -2.4235

Max Act: 1.9517. Min Act: -0.0000

Data Index: 1447369 (Python Code)

Max Activating Token Index: 269

Text #14

Max Range: 2.4235. Min Range: -2.4235

Max Act: 1.8204. Min Act: -0.0000

Data Index: 1647548 (Python Code)

Max Activating Token Index: 150

Text #15

Max Range: 2.4235. Min Range: -2.4235

Max Act: 1.9211. Min Act: -0.0000

Data Index: 1400972 (Python Code)

Max Activating Token Index: 254

Text #16

Max Range: 2.4235. Min Range: -2.4235

Max Act: 1.9024. Min Act: -0.0000

Data Index: 1377613 (Python Code)

Max Activating Token Index: 733

Text #17

Max Range: 2.4235. Min Range: -2.4235

Max Act: 1.8905. Min Act: -0.0000

Data Index: 781549 (C4 (Web Text))

Max Activating Token Index: 761

Text #18

Max Range: 2.4235. Min Range: -2.4235

Max Act: 1.8904. Min Act: -0.0000

Data Index: 1171750 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 2.4235. Min Range: -2.4235

Max Act: 1.7752. Min Act: -0.0000

Data Index: 228597 (C4 (Web Text))

Max Activating Token Index: 847