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

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

Neuron 674 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4606. Min Range: -1.4606

Max Act: 1.4606. Min Act: -0.0000

Data Index: 777479 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 1.4606. Min Range: -1.4606

Max Act: 1.1827. Min Act: -0.0000

Data Index: 1177478 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 1.4606. Min Range: -1.4606

Max Act: 1.1431. Min Act: -0.0000

Data Index: 133175 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 1.4606. Min Range: -1.4606

Max Act: 1.1065. Min Act: -0.0000

Data Index: 519033 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 1.4606. Min Range: -1.4606

Max Act: 1.1772. Min Act: -0.0000

Data Index: 818081 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 1.4606. Min Range: -1.4606

Max Act: 1.0276. Min Act: -0.0000

Data Index: 1308131 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 1.4606. Min Range: -1.4606

Max Act: 0.9972. Min Act: -0.0000

Data Index: 880536 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 1.4606. Min Range: -1.4606

Max Act: 0.9941. Min Act: -0.0000

Data Index: 270108 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 1.4606. Min Range: -1.4606

Max Act: 0.9774. Min Act: -0.0000

Data Index: 804711 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 1.4606. Min Range: -1.4606

Max Act: 0.9723. Min Act: -0.0000

Data Index: 578170 (C4 (Web Text))

Max Activating Token Index: 76

Text #10

Max Range: 1.4606. Min Range: -1.4606

Max Act: 0.9126. Min Act: -0.0000

Data Index: 494558 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 1.4606. Min Range: -1.4606

Max Act: 0.9406. Min Act: -0.0000

Data Index: 1084921 (C4 (Web Text))

Max Activating Token Index: 376

Text #12

Max Range: 1.4606. Min Range: -1.4606

Max Act: 0.9925. Min Act: -0.0000

Data Index: 44921 (C4 (Web Text))

Max Activating Token Index: 312

Text #13

Max Range: 1.4606. Min Range: -1.4606

Max Act: 0.8161. Min Act: -0.0000

Data Index: 731909 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 1.4606. Min Range: -1.4606

Max Act: 0.9249. Min Act: -0.0000

Data Index: 1347045 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 1.4606. Min Range: -1.4606

Max Act: 0.9548. Min Act: -0.0000

Data Index: 659220 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 1.4606. Min Range: -1.4606

Max Act: 0.9350. Min Act: -0.0000

Data Index: 1127684 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 1.4606. Min Range: -1.4606

Max Act: 0.9264. Min Act: -0.0000

Data Index: 1593152 (Python Code)

Max Activating Token Index: 848

Text #18

Max Range: 1.4606. Min Range: -1.4606

Max Act: 0.9225. Min Act: -0.0000

Data Index: 1137743 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 1.4606. Min Range: -1.4606

Max Act: 0.8952. Min Act: -0.0000

Data Index: 454974 (C4 (Web Text))

Max Activating Token Index: 111