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

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

Neuron 2571 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0345. Min Range: -1.0345

Max Act: 0.9889. Min Act: -0.0001

Data Index: 701762 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 1.0345. Min Range: -1.0345

Max Act: 0.9625. Min Act: -0.0001

Data Index: 723923 (C4 (Web Text))

Max Activating Token Index: 912

Text #2

Max Range: 1.0345. Min Range: -1.0345

Max Act: 1.0278. Min Act: -0.0001

Data Index: 1329059 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 1.0345. Min Range: -1.0345

Max Act: 0.9782. Min Act: -0.0001

Data Index: 665523 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 1.0345. Min Range: -1.0345

Max Act: 1.0345. Min Act: -0.0001

Data Index: 1010830 (C4 (Web Text))

Max Activating Token Index: 856

Text #5

Max Range: 1.0345. Min Range: -1.0345

Max Act: 1.0147. Min Act: -0.0001

Data Index: 867076 (C4 (Web Text))

Max Activating Token Index: 736

Text #6

Max Range: 1.0345. Min Range: -1.0345

Max Act: 0.9835. Min Act: -0.0001

Data Index: 1285934 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 1.0345. Min Range: -1.0345

Max Act: 0.9642. Min Act: -0.0001

Data Index: 13589 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 1.0345. Min Range: -1.0345

Max Act: 0.8780. Min Act: -0.0001

Data Index: 1161270 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 1.0345. Min Range: -1.0345

Max Act: 0.9631. Min Act: -0.0001

Data Index: 1043262 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 1.0345. Min Range: -1.0345

Max Act: 0.9565. Min Act: -0.0001

Data Index: 586316 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 1.0345. Min Range: -1.0345

Max Act: 0.9564. Min Act: -0.0001

Data Index: 772916 (C4 (Web Text))

Max Activating Token Index: 215

Text #12

Max Range: 1.0345. Min Range: -1.0345

Max Act: 0.9258. Min Act: -0.0001

Data Index: 214728 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 1.0345. Min Range: -1.0345

Max Act: 0.9689. Min Act: -0.0001

Data Index: 700738 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 1.0345. Min Range: -1.0345

Max Act: 0.9606. Min Act: -0.0001

Data Index: 1102989 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 1.0345. Min Range: -1.0345

Max Act: 0.9071. Min Act: -0.0001

Data Index: 867163 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 1.0345. Min Range: -1.0345

Max Act: 0.9195. Min Act: -0.0001

Data Index: 31322 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 1.0345. Min Range: -1.0345

Max Act: 0.9474. Min Act: -0.0001

Data Index: 1274225 (C4 (Web Text))

Max Activating Token Index: 556

Text #18

Max Range: 1.0345. Min Range: -1.0345

Max Act: 0.9201. Min Act: -0.0001

Data Index: 127307 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 1.0345. Min Range: -1.0345

Max Act: 0.9469. Min Act: -0.0001

Data Index: 1290966 (C4 (Web Text))

Max Activating Token Index: 754