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

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

Neuron 4119 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.7260. Min Act: -0.0001

Data Index: 462271 (C4 (Web Text))

Max Activating Token Index: 415

Text #1

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.5972. Min Act: -0.0001

Data Index: 306801 (C4 (Web Text))

Max Activating Token Index: 369

Text #2

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.4445. Min Act: -0.0001

Data Index: 428019 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.4568. Min Act: -0.0001

Data Index: 805275 (C4 (Web Text))

Max Activating Token Index: 814

Text #4

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.4293. Min Act: -0.0001

Data Index: 926660 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.4201. Min Act: -0.0001

Data Index: 57356 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.3802. Min Act: -0.0001

Data Index: 1309510 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.3334. Min Act: -0.0001

Data Index: 841075 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.3896. Min Act: -0.0001

Data Index: 379544 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.3418. Min Act: -0.0001

Data Index: 173123 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.3747. Min Act: -0.0001

Data Index: 618248 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.3954. Min Act: -0.0001

Data Index: 500905 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.3545. Min Act: -0.0001

Data Index: 362543 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.3611. Min Act: -0.0001

Data Index: 1252655 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.3242. Min Act: -0.0001

Data Index: 911472 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.3084. Min Act: -0.0001

Data Index: 1054429 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.3368. Min Act: -0.0001

Data Index: 1240236 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.3360. Min Act: -0.0001

Data Index: 1291010 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.3054. Min Act: -0.0001

Data Index: 467704 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.3252. Min Act: -0.0001

Data Index: 763922 (C4 (Web Text))

Max Activating Token Index: 25