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

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

Neuron 90 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3838. Min Range: -5.3838

Max Act: 5.3838. Min Act: -0.0000

Data Index: 1112244 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 5.3838. Min Range: -5.3838

Max Act: 5.1702. Min Act: -0.0000

Data Index: 321363 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 5.3838. Min Range: -5.3838

Max Act: 4.8228. Min Act: -0.0000

Data Index: 424606 (C4 (Web Text))

Max Activating Token Index: 241

Text #3

Max Range: 5.3838. Min Range: -5.3838

Max Act: 4.7048. Min Act: -0.0000

Data Index: 1057679 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 5.3838. Min Range: -5.3838

Max Act: 4.7003. Min Act: -0.0000

Data Index: 877355 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 5.3838. Min Range: -5.3838

Max Act: 4.4030. Min Act: -0.0000

Data Index: 284061 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 5.3838. Min Range: -5.3838

Max Act: 4.2970. Min Act: -0.0000

Data Index: 1213944 (C4 (Web Text))

Max Activating Token Index: 486

Text #7

Max Range: 5.3838. Min Range: -5.3838

Max Act: 4.3692. Min Act: -0.0000

Data Index: 989203 (C4 (Web Text))

Max Activating Token Index: 770

Text #8

Max Range: 5.3838. Min Range: -5.3838

Max Act: 4.1826. Min Act: -0.0000

Data Index: 665566 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 5.3838. Min Range: -5.3838

Max Act: 3.9440. Min Act: -0.0000

Data Index: 794148 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 5.3838. Min Range: -5.3838

Max Act: 3.9832. Min Act: -0.0000

Data Index: 417640 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 5.3838. Min Range: -5.3838

Max Act: 3.9558. Min Act: -0.0000

Data Index: 478987 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 5.3838. Min Range: -5.3838

Max Act: 3.9177. Min Act: -0.0000

Data Index: 30572 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 5.3838. Min Range: -5.3838

Max Act: 3.7301. Min Act: -0.0000

Data Index: 1082538 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 5.3838. Min Range: -5.3838

Max Act: 3.8997. Min Act: -0.0000

Data Index: 563571 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 5.3838. Min Range: -5.3838

Max Act: 3.7262. Min Act: -0.0000

Data Index: 805802 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 5.3838. Min Range: -5.3838

Max Act: 3.8220. Min Act: -0.0000

Data Index: 295406 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 5.3838. Min Range: -5.3838

Max Act: 3.6191. Min Act: -0.0000

Data Index: 1176813 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 5.3838. Min Range: -5.3838

Max Act: 3.8716. Min Act: -0.0000

Data Index: 379955 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 5.3838. Min Range: -5.3838

Max Act: 3.7052. Min Act: -0.0000

Data Index: 1236439 (C4 (Web Text))

Max Activating Token Index: 175