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

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

Neuron 1709 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: 1.3500. Min Range: -1.3500

Max Act: 1.3500. Min Act: -0.0000

Data Index: 258649 (C4 (Web Text))

Max Activating Token Index: 599

Text #1

Max Range: 1.3500. Min Range: -1.3500

Max Act: 1.3205. Min Act: -0.0001

Data Index: 300297 (C4 (Web Text))

Max Activating Token Index: 369

Text #2

Max Range: 1.3500. Min Range: -1.3500

Max Act: 1.2905. Min Act: -0.0000

Data Index: 840928 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 1.3500. Min Range: -1.3500

Max Act: 1.1574. Min Act: -0.0000

Data Index: 887472 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 1.3500. Min Range: -1.3500

Max Act: 1.1805. Min Act: -0.0001

Data Index: 1016883 (C4 (Web Text))

Max Activating Token Index: 1019

Text #5

Max Range: 1.3500. Min Range: -1.3500

Max Act: 1.1454. Min Act: -0.0000

Data Index: 198586 (C4 (Web Text))

Max Activating Token Index: 960

Text #6

Max Range: 1.3500. Min Range: -1.3500

Max Act: 1.1995. Min Act: -0.0001

Data Index: 560946 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 1.3500. Min Range: -1.3500

Max Act: 1.1476. Min Act: -0.0001

Data Index: 911692 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 1.3500. Min Range: -1.3500

Max Act: 1.0979. Min Act: -0.0001

Data Index: 596133 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 1.3500. Min Range: -1.3500

Max Act: 1.0644. Min Act: -0.0001

Data Index: 967415 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 1.3500. Min Range: -1.3500

Max Act: 1.1303. Min Act: -0.0001

Data Index: 177773 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 1.3500. Min Range: -1.3500

Max Act: 0.9799. Min Act: -0.0001

Data Index: 605687 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 1.3500. Min Range: -1.3500

Max Act: 1.0373. Min Act: -0.0001

Data Index: 1327158 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 1.3500. Min Range: -1.3500

Max Act: 1.0270. Min Act: -0.0000

Data Index: 604868 (C4 (Web Text))

Max Activating Token Index: 491

Text #14

Max Range: 1.3500. Min Range: -1.3500

Max Act: 1.0154. Min Act: -0.0001

Data Index: 914421 (C4 (Web Text))

Max Activating Token Index: 1017

Text #15

Max Range: 1.3500. Min Range: -1.3500

Max Act: 0.9993. Min Act: -0.0001

Data Index: 1206005 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 1.3500. Min Range: -1.3500

Max Act: 0.9888. Min Act: -0.0001

Data Index: 539831 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 1.3500. Min Range: -1.3500

Max Act: 1.0149. Min Act: -0.0001

Data Index: 1417068 (Python Code)

Max Activating Token Index: 477

Text #18

Max Range: 1.3500. Min Range: -1.3500

Max Act: 0.9815. Min Act: -0.0001

Data Index: 1138732 (C4 (Web Text))

Max Activating Token Index: 133

Text #19

Max Range: 1.3500. Min Range: -1.3500

Max Act: 1.0398. Min Act: -0.0001

Data Index: 58375 (C4 (Web Text))

Max Activating Token Index: 948