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

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

Neuron 1704 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6839. Min Range: -1.6839

Max Act: 1.6538. Min Act: -0.0000

Data Index: 281584 (C4 (Web Text))

Max Activating Token Index: 343

Text #1

Max Range: 1.6839. Min Range: -1.6839

Max Act: 1.6839. Min Act: -0.0000

Data Index: 634120 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 1.6839. Min Range: -1.6839

Max Act: 1.6054. Min Act: -0.0000

Data Index: 758166 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 1.6839. Min Range: -1.6839

Max Act: 1.5853. Min Act: -0.0000

Data Index: 267494 (C4 (Web Text))

Max Activating Token Index: 363

Text #4

Max Range: 1.6839. Min Range: -1.6839

Max Act: 1.5270. Min Act: -0.0000

Data Index: 1115860 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 1.6839. Min Range: -1.6839

Max Act: 1.5259. Min Act: -0.0000

Data Index: 646725 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 1.6839. Min Range: -1.6839

Max Act: 1.5177. Min Act: -0.0000

Data Index: 594064 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 1.6839. Min Range: -1.6839

Max Act: 1.3953. Min Act: -0.0000

Data Index: 76100 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 1.6839. Min Range: -1.6839

Max Act: 1.4427. Min Act: -0.0000

Data Index: 1178568 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 1.6839. Min Range: -1.6839

Max Act: 1.4373. Min Act: -0.0000

Data Index: 67030 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 1.6839. Min Range: -1.6839

Max Act: 1.5917. Min Act: -0.0000

Data Index: 1016737 (C4 (Web Text))

Max Activating Token Index: 672

Text #11

Max Range: 1.6839. Min Range: -1.6839

Max Act: 1.3829. Min Act: -0.0000

Data Index: 861820 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 1.6839. Min Range: -1.6839

Max Act: 1.3855. Min Act: -0.0000

Data Index: 308532 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 1.6839. Min Range: -1.6839

Max Act: 1.3339. Min Act: -0.0000

Data Index: 279135 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 1.6839. Min Range: -1.6839

Max Act: 1.3254. Min Act: -0.0000

Data Index: 349725 (C4 (Web Text))

Max Activating Token Index: 368

Text #15

Max Range: 1.6839. Min Range: -1.6839

Max Act: 1.3155. Min Act: -0.0000

Data Index: 967864 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 1.6839. Min Range: -1.6839

Max Act: 1.3009. Min Act: -0.0000

Data Index: 86157 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 1.6839. Min Range: -1.6839

Max Act: 1.2799. Min Act: -0.0000

Data Index: 64054 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 1.6839. Min Range: -1.6839

Max Act: 1.3257. Min Act: -0.0000

Data Index: 162087 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 1.6839. Min Range: -1.6839

Max Act: 1.3124. Min Act: -0.0000

Data Index: 755086 (C4 (Web Text))

Max Activating Token Index: 800