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

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

Neuron 815 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.8648. Min Act: -0.0001

Data Index: 522347 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.8552. Min Act: -0.0001

Data Index: 953375 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7531. Min Act: -0.0001

Data Index: 632303 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7176. Min Act: -0.0001

Data Index: 137347 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7399. Min Act: -0.0001

Data Index: 391510 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7093. Min Act: -0.0001

Data Index: 484663 (C4 (Web Text))

Max Activating Token Index: 755

Text #6

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6725. Min Act: -0.0001

Data Index: 508542 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6873. Min Act: -0.0001

Data Index: 261311 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6761. Min Act: -0.0001

Data Index: 1268498 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6520. Min Act: -0.0001

Data Index: 276222 (C4 (Web Text))

Max Activating Token Index: 791

Text #10

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6623. Min Act: -0.0001

Data Index: 678163 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6556. Min Act: -0.0001

Data Index: 524989 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6154. Min Act: -0.0001

Data Index: 1220977 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6354. Min Act: -0.0001

Data Index: 1330274 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6023. Min Act: -0.0001

Data Index: 241939 (C4 (Web Text))

Max Activating Token Index: 471

Text #15

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6452. Min Act: -0.0001

Data Index: 952105 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6148. Min Act: -0.0001

Data Index: 579326 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.5798. Min Act: -0.0001

Data Index: 570517 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6403. Min Act: -0.0001

Data Index: 781317 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6150. Min Act: -0.0001

Data Index: 574998 (C4 (Web Text))

Max Activating Token Index: 125