Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1554 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.4878. Min Range: -3.4878

Max Act: 3.4878. Min Act: -0.0001

Data Index: 1299105 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 3.4878. Min Range: -3.4878

Max Act: 3.3636. Min Act: -0.0001

Data Index: 472125 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 3.4878. Min Range: -3.4878

Max Act: 3.2946. Min Act: -0.0001

Data Index: 1120849 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 3.4878. Min Range: -3.4878

Max Act: 3.0897. Min Act: -0.0001

Data Index: 189326 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 3.4878. Min Range: -3.4878

Max Act: 3.0899. Min Act: -0.0000

Data Index: 518739 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 3.4878. Min Range: -3.4878

Max Act: 2.9491. Min Act: -0.0001

Data Index: 1108496 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 3.4878. Min Range: -3.4878

Max Act: 2.7568. Min Act: -0.0001

Data Index: 1416967 (Python Code)

Max Activating Token Index: 873

Text #7

Max Range: 3.4878. Min Range: -3.4878

Max Act: 2.8750. Min Act: -0.0001

Data Index: 1515637 (Python Code)

Max Activating Token Index: 745

Text #8

Max Range: 3.4878. Min Range: -3.4878

Max Act: 2.6591. Min Act: -0.0001

Data Index: 147846 (C4 (Web Text))

Max Activating Token Index: 379

Text #9

Max Range: 3.4878. Min Range: -3.4878

Max Act: 2.7324. Min Act: -0.0001

Data Index: 345427 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 3.4878. Min Range: -3.4878

Max Act: 2.5016. Min Act: -0.0001

Data Index: 1471318 (Python Code)

Max Activating Token Index: 739

Text #11

Max Range: 3.4878. Min Range: -3.4878

Max Act: 2.6175. Min Act: -0.0001

Data Index: 696414 (C4 (Web Text))

Max Activating Token Index: 732

Text #12

Max Range: 3.4878. Min Range: -3.4878

Max Act: 2.6255. Min Act: -0.0001

Data Index: 1030700 (C4 (Web Text))

Max Activating Token Index: 369

Text #13

Max Range: 3.4878. Min Range: -3.4878

Max Act: 2.5846. Min Act: -0.0001

Data Index: 1418823 (Python Code)

Max Activating Token Index: 318

Text #14

Max Range: 3.4878. Min Range: -3.4878

Max Act: 2.4540. Min Act: -0.0001

Data Index: 1644416 (Python Code)

Max Activating Token Index: 753

Text #15

Max Range: 3.4878. Min Range: -3.4878

Max Act: 2.4241. Min Act: -0.0000

Data Index: 613597 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 3.4878. Min Range: -3.4878

Max Act: 2.4256. Min Act: -0.0000

Data Index: 996105 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 3.4878. Min Range: -3.4878

Max Act: 2.5379. Min Act: -0.0000

Data Index: 3419 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 3.4878. Min Range: -3.4878

Max Act: 2.3723. Min Act: -0.0000

Data Index: 1314087 (C4 (Web Text))

Max Activating Token Index: 959

Text #19

Max Range: 3.4878. Min Range: -3.4878

Max Act: 2.5256. Min Act: -0.0001

Data Index: 1027369 (C4 (Web Text))

Max Activating Token Index: 296