Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 2038 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.1215. Min Range: -4.1215

Max Act: 4.1215. Min Act: -0.1700

Data Index: 1165109 (C4 (Web Text))

Max Activating Token Index: 792

Text #1

Max Range: 4.1215. Min Range: -4.1215

Max Act: 4.0817. Min Act: -0.1700

Data Index: 234078 (C4 (Web Text))

Max Activating Token Index: 735

Text #2

Max Range: 4.1215. Min Range: -4.1215

Max Act: 4.0794. Min Act: -0.1700

Data Index: 1223602 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 4.1215. Min Range: -4.1215

Max Act: 4.0834. Min Act: -0.1699

Data Index: 743114 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 4.1215. Min Range: -4.1215

Max Act: 4.0915. Min Act: -0.1700

Data Index: 1125892 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 4.1215. Min Range: -4.1215

Max Act: 4.0867. Min Act: -0.1700

Data Index: 181819 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 4.1215. Min Range: -4.1215

Max Act: 4.0538. Min Act: -0.1700

Data Index: 625653 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 4.1215. Min Range: -4.1215

Max Act: 4.0452. Min Act: -0.1700

Data Index: 467794 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 4.1215. Min Range: -4.1215

Max Act: 4.0492. Min Act: -0.1700

Data Index: 1290923 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 4.1215. Min Range: -4.1215

Max Act: 4.0489. Min Act: -0.1700

Data Index: 1292539 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 4.1215. Min Range: -4.1215

Max Act: 4.0566. Min Act: -0.1700

Data Index: 819835 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 4.1215. Min Range: -4.1215

Max Act: 4.0560. Min Act: -0.1700

Data Index: 1350703 (C4 (Web Text))

Max Activating Token Index: 882

Text #12

Max Range: 4.1215. Min Range: -4.1215

Max Act: 4.0384. Min Act: -0.1700

Data Index: 235317 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 4.1215. Min Range: -4.1215

Max Act: 4.0214. Min Act: -0.1700

Data Index: 384329 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 4.1215. Min Range: -4.1215

Max Act: 4.0421. Min Act: -0.1700

Data Index: 1076758 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 4.1215. Min Range: -4.1215

Max Act: 4.0243. Min Act: -0.1700

Data Index: 259600 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 4.1215. Min Range: -4.1215

Max Act: 4.0072. Min Act: -0.1700

Data Index: 738844 (C4 (Web Text))

Max Activating Token Index: 891

Text #17

Max Range: 4.1215. Min Range: -4.1215

Max Act: 3.9921. Min Act: -0.1700

Data Index: 467888 (C4 (Web Text))

Max Activating Token Index: 588

Text #18

Max Range: 4.1215. Min Range: -4.1215

Max Act: 3.9904. Min Act: -0.1700

Data Index: 313063 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 4.1215. Min Range: -4.1215

Max Act: 3.9979. Min Act: -0.1700

Data Index: 679966 (C4 (Web Text))

Max Activating Token Index: 469