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

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

Neuron 3675 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4501. Min Range: -2.4501

Max Act: 2.2435. Min Act: -0.0000

Data Index: 1380317 (Python Code)

Max Activating Token Index: 829

Text #1

Max Range: 2.4501. Min Range: -2.4501

Max Act: 2.1810. Min Act: -0.0000

Data Index: 276626 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 2.4501. Min Range: -2.4501

Max Act: 2.1003. Min Act: -0.0000

Data Index: 1647895 (Python Code)

Max Activating Token Index: 546

Text #3

Max Range: 2.4501. Min Range: -2.4501

Max Act: 2.2752. Min Act: -0.0000

Data Index: 1486914 (Python Code)

Max Activating Token Index: 323

Text #4

Max Range: 2.4501. Min Range: -2.4501

Max Act: 2.4501. Min Act: -0.0000

Data Index: 1119868 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 2.4501. Min Range: -2.4501

Max Act: 2.2628. Min Act: -0.0001

Data Index: 355391 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 2.4501. Min Range: -2.4501

Max Act: 1.8755. Min Act: -0.0000

Data Index: 1282467 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 2.4501. Min Range: -2.4501

Max Act: 1.9706. Min Act: -0.0000

Data Index: 330507 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 2.4501. Min Range: -2.4501

Max Act: 1.9200. Min Act: -0.0001

Data Index: 754526 (C4 (Web Text))

Max Activating Token Index: 410

Text #9

Max Range: 2.4501. Min Range: -2.4501

Max Act: 2.0906. Min Act: -0.0001

Data Index: 1573679 (Python Code)

Max Activating Token Index: 905

Text #10

Max Range: 2.4501. Min Range: -2.4501

Max Act: 1.8925. Min Act: -0.0000

Data Index: 333522 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 2.4501. Min Range: -2.4501

Max Act: 1.9769. Min Act: -0.0001

Data Index: 1197591 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 2.4501. Min Range: -2.4501

Max Act: 2.0198. Min Act: -0.0000

Data Index: 1441823 (Python Code)

Max Activating Token Index: 696

Text #13

Max Range: 2.4501. Min Range: -2.4501

Max Act: 1.9160. Min Act: -0.0000

Data Index: 1479568 (Python Code)

Max Activating Token Index: 912

Text #14

Max Range: 2.4501. Min Range: -2.4501

Max Act: 1.8172. Min Act: -0.0000

Data Index: 1553602 (Python Code)

Max Activating Token Index: 725

Text #15

Max Range: 2.4501. Min Range: -2.4501

Max Act: 1.8327. Min Act: -0.0001

Data Index: 791700 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 2.4501. Min Range: -2.4501

Max Act: 1.7187. Min Act: -0.0000

Data Index: 37431 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 2.4501. Min Range: -2.4501

Max Act: 1.9128. Min Act: -0.0000

Data Index: 1570822 (Python Code)

Max Activating Token Index: 955

Text #18

Max Range: 2.4501. Min Range: -2.4501

Max Act: 1.9204. Min Act: -0.0000

Data Index: 1479186 (Python Code)

Max Activating Token Index: 526

Text #19

Max Range: 2.4501. Min Range: -2.4501

Max Act: 1.7816. Min Act: -0.0001

Data Index: 34578 (C4 (Web Text))

Max Activating Token Index: 933