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

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

Neuron 103 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.4373. Min Act: -0.0000

Data Index: 138569 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.3079. Min Act: -0.0000

Data Index: 772028 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.1840. Min Act: -0.0000

Data Index: 523973 (C4 (Web Text))

Max Activating Token Index: 368

Text #3

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.1519. Min Act: -0.0000

Data Index: 1206861 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.3193. Min Act: -0.0000

Data Index: 86417 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.1823. Min Act: -0.0000

Data Index: 271853 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.2219. Min Act: 0.0001

Data Index: 265946 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.1530. Min Act: 0.0002

Data Index: 1137962 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.1886. Min Act: 0.0001

Data Index: 247912 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.1332. Min Act: -0.0000

Data Index: 1098390 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.2532. Min Act: -0.0000

Data Index: 617720 (C4 (Web Text))

Max Activating Token Index: 403

Text #11

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.1323. Min Act: -0.0000

Data Index: 976076 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.1084. Min Act: -0.0000

Data Index: 15561 (C4 (Web Text))

Max Activating Token Index: 368

Text #13

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.0772. Min Act: -0.0000

Data Index: 1154813 (C4 (Web Text))

Max Activating Token Index: 613

Text #14

Max Range: 1.4373. Min Range: -1.4373

Max Act: 0.9799. Min Act: -0.0000

Data Index: 1197684 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.0500. Min Act: 0.0001

Data Index: 634081 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.0082. Min Act: 0.0000

Data Index: 603300 (C4 (Web Text))

Max Activating Token Index: 191

Text #17

Max Range: 1.4373. Min Range: -1.4373

Max Act: 0.8886. Min Act: 0.0001

Data Index: 827508 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 1.4373. Min Range: -1.4373

Max Act: 0.9234. Min Act: -0.0000

Data Index: 229091 (C4 (Web Text))

Max Activating Token Index: 818

Text #19

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.1198. Min Act: -0.0000

Data Index: 607896 (C4 (Web Text))

Max Activating Token Index: 185