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

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

Neuron 3567 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.6768. Min Act: -0.0000

Data Index: 994865 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.6511. Min Act: -0.0000

Data Index: 984981 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.6013. Min Act: -0.0000

Data Index: 512846 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5696. Min Act: -0.0000

Data Index: 10055 (C4 (Web Text))

Max Activating Token Index: 398

Text #4

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5609. Min Act: -0.0000

Data Index: 770346 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5442. Min Act: -0.0000

Data Index: 809877 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5346. Min Act: -0.0000

Data Index: 1322241 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5533. Min Act: -0.0000

Data Index: 666713 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5672. Min Act: -0.0000

Data Index: 971513 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5440. Min Act: -0.0000

Data Index: 758356 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5489. Min Act: -0.0000

Data Index: 1082614 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5526. Min Act: -0.0000

Data Index: 379413 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5213. Min Act: -0.0000

Data Index: 651326 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5176. Min Act: -0.0000

Data Index: 748931 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5453. Min Act: -0.0000

Data Index: 239691 (C4 (Web Text))

Max Activating Token Index: 376

Text #15

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5463. Min Act: -0.0000

Data Index: 768770 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5481. Min Act: -0.0000

Data Index: 109188 (C4 (Web Text))

Max Activating Token Index: 542

Text #17

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5569. Min Act: -0.0000

Data Index: 382941 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.4895. Min Act: -0.0000

Data Index: 885421 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5384. Min Act: -0.0000

Data Index: 897635 (C4 (Web Text))

Max Activating Token Index: 532