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

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

Neuron 3375 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3360. Min Range: -1.3360

Max Act: 1.3360. Min Act: -0.0000

Data Index: 302084 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 1.3360. Min Range: -1.3360

Max Act: 1.1532. Min Act: -0.0000

Data Index: 833594 (C4 (Web Text))

Max Activating Token Index: 285

Text #2

Max Range: 1.3360. Min Range: -1.3360

Max Act: 1.1378. Min Act: -0.0000

Data Index: 794243 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 1.3360. Min Range: -1.3360

Max Act: 0.9057. Min Act: -0.0000

Data Index: 85606 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 1.3360. Min Range: -1.3360

Max Act: 1.0688. Min Act: -0.0000

Data Index: 579860 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 1.3360. Min Range: -1.3360

Max Act: 0.8157. Min Act: -0.0000

Data Index: 762810 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 1.3360. Min Range: -1.3360

Max Act: 0.9140. Min Act: -0.0000

Data Index: 631892 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 1.3360. Min Range: -1.3360

Max Act: 0.7709. Min Act: -0.0000

Data Index: 991494 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 1.3360. Min Range: -1.3360

Max Act: 0.8589. Min Act: -0.0000

Data Index: 561014 (C4 (Web Text))

Max Activating Token Index: 476

Text #9

Max Range: 1.3360. Min Range: -1.3360

Max Act: 0.8565. Min Act: -0.0000

Data Index: 122652 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 1.3360. Min Range: -1.3360

Max Act: 0.8224. Min Act: -0.0000

Data Index: 701373 (C4 (Web Text))

Max Activating Token Index: 376

Text #11

Max Range: 1.3360. Min Range: -1.3360

Max Act: 0.7295. Min Act: -0.0000

Data Index: 567803 (C4 (Web Text))

Max Activating Token Index: 519

Text #12

Max Range: 1.3360. Min Range: -1.3360

Max Act: 0.6567. Min Act: -0.0000

Data Index: 1116544 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 1.3360. Min Range: -1.3360

Max Act: 0.7677. Min Act: -0.0000

Data Index: 919549 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 1.3360. Min Range: -1.3360

Max Act: 0.6540. Min Act: -0.0000

Data Index: 1080931 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 1.3360. Min Range: -1.3360

Max Act: 0.6406. Min Act: -0.0000

Data Index: 1053494 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 1.3360. Min Range: -1.3360

Max Act: 0.6801. Min Act: -0.0000

Data Index: 495857 (C4 (Web Text))

Max Activating Token Index: 835

Text #17

Max Range: 1.3360. Min Range: -1.3360

Max Act: 0.6320. Min Act: -0.0000

Data Index: 1016817 (C4 (Web Text))

Max Activating Token Index: 280

Text #18

Max Range: 1.3360. Min Range: -1.3360

Max Act: 0.6510. Min Act: -0.0000

Data Index: 444963 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 1.3360. Min Range: -1.3360

Max Act: 0.6072. Min Act: -0.0000

Data Index: 1142709 (C4 (Web Text))

Max Activating Token Index: 809