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

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

Neuron 3346 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2950. Min Act: -0.0001

Data Index: 1183820 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2340. Min Act: -0.0001

Data Index: 749843 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2213. Min Act: -0.0001

Data Index: 1301817 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2253. Min Act: -0.0001

Data Index: 814109 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.1919. Min Act: -0.0001

Data Index: 840061 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.1946. Min Act: -0.0001

Data Index: 435676 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.1928. Min Act: -0.0001

Data Index: 1035047 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.1849. Min Act: -0.0001

Data Index: 168524 (C4 (Web Text))

Max Activating Token Index: 336

Text #8

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2015. Min Act: -0.0001

Data Index: 300043 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.1985. Min Act: -0.0001

Data Index: 1255397 (C4 (Web Text))

Max Activating Token Index: 451

Text #10

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.1905. Min Act: -0.0001

Data Index: 1037476 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.1872. Min Act: -0.0001

Data Index: 465287 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.1866. Min Act: -0.0001

Data Index: 497170 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.1915. Min Act: -0.0001

Data Index: 375857 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.1830. Min Act: -0.0001

Data Index: 769681 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.1823. Min Act: -0.0001

Data Index: 738896 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.1825. Min Act: -0.0001

Data Index: 786315 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.1587. Min Act: -0.0001

Data Index: 242774 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.1739. Min Act: -0.0001

Data Index: 559029 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.1736. Min Act: -0.0001

Data Index: 141042 (C4 (Web Text))

Max Activating Token Index: 50