Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1192 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.1781. Min Range: -5.1781

Max Act: 5.1781. Min Act: -0.1700

Data Index: 499862 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 5.1781. Min Range: -5.1781

Max Act: 4.9906. Min Act: -0.1700

Data Index: 333825 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 5.1781. Min Range: -5.1781

Max Act: 4.9593. Min Act: -0.1700

Data Index: 860606 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 5.1781. Min Range: -5.1781

Max Act: 4.9281. Min Act: -0.1699

Data Index: 663925 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 5.1781. Min Range: -5.1781

Max Act: 4.9281. Min Act: -0.1700

Data Index: 825608 (C4 (Web Text))

Max Activating Token Index: 144

Text #5

Max Range: 5.1781. Min Range: -5.1781

Max Act: 4.9906. Min Act: -0.1700

Data Index: 435907 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 5.1781. Min Range: -5.1781

Max Act: 4.8968. Min Act: -0.1700

Data Index: 269299 (C4 (Web Text))

Max Activating Token Index: 532

Text #7

Max Range: 5.1781. Min Range: -5.1781

Max Act: 4.8343. Min Act: -0.1700

Data Index: 201798 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 5.1781. Min Range: -5.1781

Max Act: 4.8656. Min Act: -0.1700

Data Index: 627975 (C4 (Web Text))

Max Activating Token Index: 310

Text #9

Max Range: 5.1781. Min Range: -5.1781

Max Act: 4.8968. Min Act: -0.1700

Data Index: 1147706 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 5.1781. Min Range: -5.1781

Max Act: 4.8656. Min Act: -0.1700

Data Index: 1285345 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 5.1781. Min Range: -5.1781

Max Act: 4.8656. Min Act: -0.1700

Data Index: 1328637 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 5.1781. Min Range: -5.1781

Max Act: 4.8656. Min Act: -0.1700

Data Index: 417205 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 5.1781. Min Range: -5.1781

Max Act: 4.8656. Min Act: -0.1700

Data Index: 1159168 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 5.1781. Min Range: -5.1781

Max Act: 4.8968. Min Act: -0.1700

Data Index: 251476 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 5.1781. Min Range: -5.1781

Max Act: 4.8031. Min Act: -0.1700

Data Index: 1261176 (C4 (Web Text))

Max Activating Token Index: 998

Text #16

Max Range: 5.1781. Min Range: -5.1781

Max Act: 4.8031. Min Act: -0.1700

Data Index: 465493 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 5.1781. Min Range: -5.1781

Max Act: 4.8656. Min Act: -0.1700

Data Index: 638590 (C4 (Web Text))

Max Activating Token Index: 983

Text #18

Max Range: 5.1781. Min Range: -5.1781

Max Act: 4.8343. Min Act: -0.1700

Data Index: 1215754 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 5.1781. Min Range: -5.1781

Max Act: 4.8656. Min Act: -0.1700

Data Index: 363789 (C4 (Web Text))

Max Activating Token Index: 432