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

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

Neuron 3139 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: 1.6236. Min Range: -1.6236

Max Act: 1.6236. Min Act: -0.0000

Data Index: 201418 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 1.6236. Min Range: -1.6236

Max Act: 1.3455. Min Act: -0.0000

Data Index: 575019 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 1.6236. Min Range: -1.6236

Max Act: 1.2611. Min Act: -0.0000

Data Index: 800909 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 1.6236. Min Range: -1.6236

Max Act: 1.3425. Min Act: -0.0000

Data Index: 1098613 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 1.6236. Min Range: -1.6236

Max Act: 1.3225. Min Act: -0.0000

Data Index: 1187383 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 1.6236. Min Range: -1.6236

Max Act: 1.2870. Min Act: -0.0000

Data Index: 358415 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 1.6236. Min Range: -1.6236

Max Act: 1.2665. Min Act: -0.0000

Data Index: 630059 (C4 (Web Text))

Max Activating Token Index: 831

Text #7

Max Range: 1.6236. Min Range: -1.6236

Max Act: 1.2184. Min Act: -0.0000

Data Index: 249139 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 1.6236. Min Range: -1.6236

Max Act: 1.1716. Min Act: -0.0000

Data Index: 1003148 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 1.6236. Min Range: -1.6236

Max Act: 1.1712. Min Act: -0.0000

Data Index: 1006133 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 1.6236. Min Range: -1.6236

Max Act: 1.1688. Min Act: -0.0000

Data Index: 1158116 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 1.6236. Min Range: -1.6236

Max Act: 1.2058. Min Act: -0.0000

Data Index: 1335597 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 1.6236. Min Range: -1.6236

Max Act: 1.2020. Min Act: -0.0000

Data Index: 519834 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 1.6236. Min Range: -1.6236

Max Act: 1.0637. Min Act: -0.0000

Data Index: 481056 (C4 (Web Text))

Max Activating Token Index: 766

Text #14

Max Range: 1.6236. Min Range: -1.6236

Max Act: 1.0937. Min Act: -0.0000

Data Index: 916491 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 1.6236. Min Range: -1.6236

Max Act: 1.1551. Min Act: -0.0000

Data Index: 1172025 (C4 (Web Text))

Max Activating Token Index: 816

Text #16

Max Range: 1.6236. Min Range: -1.6236

Max Act: 1.1222. Min Act: -0.0000

Data Index: 189888 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 1.6236. Min Range: -1.6236

Max Act: 1.2241. Min Act: -0.0000

Data Index: 406908 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 1.6236. Min Range: -1.6236

Max Act: 1.1340. Min Act: -0.0000

Data Index: 339599 (C4 (Web Text))

Max Activating Token Index: 498

Text #19

Max Range: 1.6236. Min Range: -1.6236

Max Act: 1.1685. Min Act: -0.0000

Data Index: 879617 (C4 (Web Text))

Max Activating Token Index: 955