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

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

Neuron 3621 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: 0.8685. Min Range: -0.8685

Max Act: 0.8510. Min Act: -0.0000

Data Index: 236631 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.8009. Min Act: -0.0000

Data Index: 812462 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.8685. Min Act: -0.0000

Data Index: 1091145 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.7794. Min Act: -0.0000

Data Index: 927710 (C4 (Web Text))

Max Activating Token Index: 468

Text #4

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.7810. Min Act: -0.0000

Data Index: 337576 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.7869. Min Act: -0.0000

Data Index: 541101 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.7671. Min Act: -0.0000

Data Index: 172073 (C4 (Web Text))

Max Activating Token Index: 777

Text #7

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.7252. Min Act: -0.0000

Data Index: 286660 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.7479. Min Act: -0.0000

Data Index: 762846 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.7369. Min Act: -0.0000

Data Index: 1029125 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.6340. Min Act: -0.0000

Data Index: 1045053 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.7298. Min Act: -0.0000

Data Index: 741179 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.6926. Min Act: -0.0000

Data Index: 822468 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.7396. Min Act: -0.0000

Data Index: 514694 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.6925. Min Act: -0.0000

Data Index: 935353 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.6796. Min Act: -0.0000

Data Index: 1146788 (C4 (Web Text))

Max Activating Token Index: 772

Text #16

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.7028. Min Act: -0.0000

Data Index: 798027 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.6660. Min Act: -0.0000

Data Index: 341056 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.6924. Min Act: -0.0000

Data Index: 887431 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.6954. Min Act: -0.0000

Data Index: 1289439 (C4 (Web Text))

Max Activating Token Index: 541