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

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

Neuron 2701 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: 0.4621. Min Range: -0.4621

Max Act: 0.4621. Min Act: -0.0000

Data Index: 135452 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.4298. Min Act: -0.0000

Data Index: 534483 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.4230. Min Act: -0.0000

Data Index: 855393 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.4069. Min Act: -0.0000

Data Index: 1135588 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.4429. Min Act: -0.0000

Data Index: 23396 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.4166. Min Act: -0.0000

Data Index: 683073 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.4139. Min Act: -0.0000

Data Index: 853077 (C4 (Web Text))

Max Activating Token Index: 504

Text #7

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.4300. Min Act: -0.0000

Data Index: 91487 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.4138. Min Act: -0.0000

Data Index: 1119937 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.4061. Min Act: -0.0000

Data Index: 797073 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3963. Min Act: -0.0000

Data Index: 42275 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.4002. Min Act: -0.0000

Data Index: 1200873 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.4091. Min Act: -0.0000

Data Index: 1321259 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3951. Min Act: -0.0000

Data Index: 6914 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3829. Min Act: -0.0000

Data Index: 1204988 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3833. Min Act: -0.0000

Data Index: 578218 (C4 (Web Text))

Max Activating Token Index: 911

Text #16

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3792. Min Act: -0.0000

Data Index: 738034 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3915. Min Act: -0.0000

Data Index: 606044 (C4 (Web Text))

Max Activating Token Index: 667

Text #18

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3985. Min Act: -0.0000

Data Index: 587918 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3850. Min Act: -0.0000

Data Index: 1139012 (C4 (Web Text))

Max Activating Token Index: 540