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

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

Neuron 3614 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3591. Min Range: -1.3591

Max Act: 1.3591. Min Act: -0.0000

Data Index: 981796 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 1.3591. Min Range: -1.3591

Max Act: 1.3331. Min Act: -0.0000

Data Index: 656560 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 1.3591. Min Range: -1.3591

Max Act: 1.3133. Min Act: -0.0000

Data Index: 665415 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 1.3591. Min Range: -1.3591

Max Act: 1.2862. Min Act: -0.0000

Data Index: 827325 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 1.3591. Min Range: -1.3591

Max Act: 1.3124. Min Act: -0.0000

Data Index: 565714 (C4 (Web Text))

Max Activating Token Index: 413

Text #5

Max Range: 1.3591. Min Range: -1.3591

Max Act: 1.3576. Min Act: -0.0000

Data Index: 181031 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 1.3591. Min Range: -1.3591

Max Act: 1.2186. Min Act: -0.0000

Data Index: 895777 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 1.3591. Min Range: -1.3591

Max Act: 1.2640. Min Act: -0.0000

Data Index: 1213795 (C4 (Web Text))

Max Activating Token Index: 336

Text #8

Max Range: 1.3591. Min Range: -1.3591

Max Act: 1.2591. Min Act: -0.0000

Data Index: 948568 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 1.3591. Min Range: -1.3591

Max Act: 1.2216. Min Act: -0.0000

Data Index: 1217208 (C4 (Web Text))

Max Activating Token Index: 427

Text #10

Max Range: 1.3591. Min Range: -1.3591

Max Act: 1.2294. Min Act: -0.0000

Data Index: 367248 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 1.3591. Min Range: -1.3591

Max Act: 1.2922. Min Act: -0.0000

Data Index: 1025005 (C4 (Web Text))

Max Activating Token Index: 678

Text #12

Max Range: 1.3591. Min Range: -1.3591

Max Act: 1.1515. Min Act: -0.0000

Data Index: 382943 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 1.3591. Min Range: -1.3591

Max Act: 1.2064. Min Act: -0.0000

Data Index: 543520 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 1.3591. Min Range: -1.3591

Max Act: 1.1607. Min Act: -0.0000

Data Index: 638115 (C4 (Web Text))

Max Activating Token Index: 737

Text #15

Max Range: 1.3591. Min Range: -1.3591

Max Act: 1.1975. Min Act: -0.0000

Data Index: 722712 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 1.3591. Min Range: -1.3591

Max Act: 1.1547. Min Act: -0.0000

Data Index: 745130 (C4 (Web Text))

Max Activating Token Index: 514

Text #17

Max Range: 1.3591. Min Range: -1.3591

Max Act: 1.1829. Min Act: -0.0000

Data Index: 1231000 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 1.3591. Min Range: -1.3591

Max Act: 1.1489. Min Act: -0.0000

Data Index: 979865 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 1.3591. Min Range: -1.3591

Max Act: 1.1757. Min Act: -0.0000

Data Index: 597849 (C4 (Web Text))

Max Activating Token Index: 403