Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4253 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5510. Min Range: -0.5510

Max Act: 0.5510. Min Act: -0.0000

Data Index: 420862 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 0.5510. Min Range: -0.5510

Max Act: 0.3430. Min Act: -0.0000

Data Index: 128407 (C4 (Web Text))

Max Activating Token Index: 519

Text #2

Max Range: 0.5510. Min Range: -0.5510

Max Act: 0.3445. Min Act: -0.0000

Data Index: 252216 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 0.5510. Min Range: -0.5510

Max Act: 0.3176. Min Act: -0.0000

Data Index: 386827 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 0.5510. Min Range: -0.5510

Max Act: 0.3272. Min Act: -0.0000

Data Index: 532946 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 0.5510. Min Range: -0.5510

Max Act: 0.3342. Min Act: -0.0000

Data Index: 997998 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 0.5510. Min Range: -0.5510

Max Act: 0.3304. Min Act: -0.0000

Data Index: 401906 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 0.5510. Min Range: -0.5510

Max Act: 0.3161. Min Act: -0.0000

Data Index: 1059307 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 0.5510. Min Range: -0.5510

Max Act: 0.2910. Min Act: -0.0000

Data Index: 1272492 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 0.5510. Min Range: -0.5510

Max Act: 0.2871. Min Act: -0.0000

Data Index: 558343 (C4 (Web Text))

Max Activating Token Index: 312

Text #10

Max Range: 0.5510. Min Range: -0.5510

Max Act: 0.3075. Min Act: -0.0000

Data Index: 942060 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 0.5510. Min Range: -0.5510

Max Act: 0.3058. Min Act: -0.0000

Data Index: 243623 (C4 (Web Text))

Max Activating Token Index: 873

Text #12

Max Range: 0.5510. Min Range: -0.5510

Max Act: 0.2989. Min Act: -0.0000

Data Index: 1157375 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 0.5510. Min Range: -0.5510

Max Act: 0.3089. Min Act: -0.0000

Data Index: 846359 (C4 (Web Text))

Max Activating Token Index: 519

Text #14

Max Range: 0.5510. Min Range: -0.5510

Max Act: 0.2829. Min Act: -0.0000

Data Index: 603431 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 0.5510. Min Range: -0.5510

Max Act: 0.2929. Min Act: -0.0000

Data Index: 741257 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.5510. Min Range: -0.5510

Max Act: 0.2904. Min Act: -0.0000

Data Index: 671993 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 0.5510. Min Range: -0.5510

Max Act: 0.2806. Min Act: -0.0000

Data Index: 145264 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 0.5510. Min Range: -0.5510

Max Act: 0.2895. Min Act: -0.0000

Data Index: 1255181 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 0.5510. Min Range: -0.5510

Max Act: 0.2874. Min Act: -0.0000

Data Index: 167893 (C4 (Web Text))

Max Activating Token Index: 364