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

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

Neuron 3111 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3600. Min Range: -1.3600

Max Act: 1.3600. Min Act: 0.0000

Data Index: 408180 (C4 (Web Text))

Max Activating Token Index: 926

Text #1

Max Range: 1.3600. Min Range: -1.3600

Max Act: 1.2203. Min Act: -0.0000

Data Index: 556295 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 1.3600. Min Range: -1.3600

Max Act: 1.2051. Min Act: 0.0001

Data Index: 463647 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 1.3600. Min Range: -1.3600

Max Act: 1.1061. Min Act: 0.0000

Data Index: 19079 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 1.3600. Min Range: -1.3600

Max Act: 1.1782. Min Act: -0.0000

Data Index: 6704 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 1.3600. Min Range: -1.3600

Max Act: 1.2181. Min Act: -0.0000

Data Index: 63949 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 1.3600. Min Range: -1.3600

Max Act: 1.1321. Min Act: -0.0000

Data Index: 28322 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 1.3600. Min Range: -1.3600

Max Act: 1.1003. Min Act: -0.0000

Data Index: 197366 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 1.3600. Min Range: -1.3600

Max Act: 1.0077. Min Act: -0.0000

Data Index: 428657 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 1.3600. Min Range: -1.3600

Max Act: 0.9942. Min Act: -0.0000

Data Index: 475297 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 1.3600. Min Range: -1.3600

Max Act: 1.0342. Min Act: -0.0000

Data Index: 244501 (C4 (Web Text))

Max Activating Token Index: 611

Text #11

Max Range: 1.3600. Min Range: -1.3600

Max Act: 1.0382. Min Act: -0.0000

Data Index: 667364 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 1.3600. Min Range: -1.3600

Max Act: 1.0282. Min Act: -0.0000

Data Index: 107106 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 1.3600. Min Range: -1.3600

Max Act: 1.0940. Min Act: -0.0000

Data Index: 1038013 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 1.3600. Min Range: -1.3600

Max Act: 1.0297. Min Act: -0.0000

Data Index: 852708 (C4 (Web Text))

Max Activating Token Index: 858

Text #15

Max Range: 1.3600. Min Range: -1.3600

Max Act: 0.9580. Min Act: -0.0000

Data Index: 1031 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 1.3600. Min Range: -1.3600

Max Act: 1.0176. Min Act: 0.0000

Data Index: 665341 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 1.3600. Min Range: -1.3600

Max Act: 1.0202. Min Act: -0.0000

Data Index: 539787 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 1.3600. Min Range: -1.3600

Max Act: 1.0120. Min Act: 0.0001

Data Index: 140845 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 1.3600. Min Range: -1.3600

Max Act: 1.0377. Min Act: -0.0000

Data Index: 916309 (C4 (Web Text))

Max Activating Token Index: 900