Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 66 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4067. Min Range: -1.4067

Max Act: 1.4067. Min Act: -0.0001

Data Index: 1296322 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 1.4067. Min Range: -1.4067

Max Act: 1.2557. Min Act: -0.0001

Data Index: 768570 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 1.4067. Min Range: -1.4067

Max Act: 1.2276. Min Act: -0.0001

Data Index: 142473 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 1.4067. Min Range: -1.4067

Max Act: 1.1532. Min Act: -0.0001

Data Index: 781012 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 1.4067. Min Range: -1.4067

Max Act: 1.3012. Min Act: -0.0001

Data Index: 1153879 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 1.4067. Min Range: -1.4067

Max Act: 1.0400. Min Act: -0.0001

Data Index: 838843 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 1.4067. Min Range: -1.4067

Max Act: 1.0838. Min Act: -0.0001

Data Index: 98043 (C4 (Web Text))

Max Activating Token Index: 447

Text #7

Max Range: 1.4067. Min Range: -1.4067

Max Act: 1.0931. Min Act: -0.0001

Data Index: 523064 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 1.4067. Min Range: -1.4067

Max Act: 0.9831. Min Act: -0.0001

Data Index: 656399 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 1.4067. Min Range: -1.4067

Max Act: 1.0425. Min Act: -0.0001

Data Index: 1307628 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 1.4067. Min Range: -1.4067

Max Act: 1.1825. Min Act: -0.0001

Data Index: 997788 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 1.4067. Min Range: -1.4067

Max Act: 0.9385. Min Act: -0.0001

Data Index: 178261 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 1.4067. Min Range: -1.4067

Max Act: 1.0169. Min Act: -0.0001

Data Index: 437000 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 1.4067. Min Range: -1.4067

Max Act: 0.8978. Min Act: -0.0001

Data Index: 431004 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 1.4067. Min Range: -1.4067

Max Act: 0.9703. Min Act: -0.0001

Data Index: 66395 (C4 (Web Text))

Max Activating Token Index: 461

Text #15

Max Range: 1.4067. Min Range: -1.4067

Max Act: 0.9376. Min Act: -0.0001

Data Index: 1107942 (C4 (Web Text))

Max Activating Token Index: 776

Text #16

Max Range: 1.4067. Min Range: -1.4067

Max Act: 0.8431. Min Act: -0.0001

Data Index: 743294 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 1.4067. Min Range: -1.4067

Max Act: 0.9209. Min Act: -0.0001

Data Index: 1297504 (C4 (Web Text))

Max Activating Token Index: 377

Text #18

Max Range: 1.4067. Min Range: -1.4067

Max Act: 1.0190. Min Act: -0.0001

Data Index: 323539 (C4 (Web Text))

Max Activating Token Index: 723

Text #19

Max Range: 1.4067. Min Range: -1.4067

Max Act: 0.9561. Min Act: -0.0001

Data Index: 1251334 (C4 (Web Text))

Max Activating Token Index: 551