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

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

Neuron 680 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: 1.0191. Min Range: -1.0191

Max Act: 1.0191. Min Act: -0.0000

Data Index: 618126 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.9209. Min Act: -0.0000

Data Index: 66839 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.8733. Min Act: -0.0000

Data Index: 1100814 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.8677. Min Act: -0.0000

Data Index: 680924 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.9521. Min Act: -0.0000

Data Index: 1239190 (C4 (Web Text))

Max Activating Token Index: 933

Text #5

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.8421. Min Act: -0.0000

Data Index: 1338995 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.8832. Min Act: -0.0000

Data Index: 904044 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.8642. Min Act: -0.0000

Data Index: 1025754 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.8439. Min Act: -0.0000

Data Index: 523552 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.8863. Min Act: -0.0000

Data Index: 1196012 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.8732. Min Act: -0.0000

Data Index: 1177862 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.8490. Min Act: -0.0000

Data Index: 773726 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.8528. Min Act: 0.0000

Data Index: 650116 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.8435. Min Act: -0.0000

Data Index: 418547 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.8411. Min Act: -0.0000

Data Index: 50236 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.8129. Min Act: -0.0000

Data Index: 1319429 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.8090. Min Act: -0.0000

Data Index: 816091 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.8010. Min Act: -0.0000

Data Index: 221437 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.8591. Min Act: -0.0000

Data Index: 48394 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.8214. Min Act: -0.0000

Data Index: 390916 (C4 (Web Text))

Max Activating Token Index: 580