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

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

Neuron 399 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: 3.8902. Min Range: -3.8902

Max Act: 3.8902. Min Act: -0.1700

Data Index: 1101712 (C4 (Web Text))

Max Activating Token Index: 358

Text #1

Max Range: 3.8902. Min Range: -3.8902

Max Act: 3.8693. Min Act: -0.1700

Data Index: 1056577 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 3.8902. Min Range: -3.8902

Max Act: 3.8645. Min Act: -0.1700

Data Index: 1341528 (C4 (Web Text))

Max Activating Token Index: 660

Text #3

Max Range: 3.8902. Min Range: -3.8902

Max Act: 3.8215. Min Act: -0.1700

Data Index: 548113 (C4 (Web Text))

Max Activating Token Index: 946

Text #4

Max Range: 3.8902. Min Range: -3.8902

Max Act: 3.8271. Min Act: -0.1700

Data Index: 818551 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 3.8902. Min Range: -3.8902

Max Act: 3.7805. Min Act: -0.1700

Data Index: 1357868 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 3.8902. Min Range: -3.8902

Max Act: 3.7732. Min Act: -0.1700

Data Index: 24652 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 3.8902. Min Range: -3.8902

Max Act: 3.7604. Min Act: -0.1700

Data Index: 893347 (C4 (Web Text))

Max Activating Token Index: 683

Text #8

Max Range: 3.8902. Min Range: -3.8902

Max Act: 3.7702. Min Act: -0.1700

Data Index: 1354653 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 3.8902. Min Range: -3.8902

Max Act: 3.7381. Min Act: -0.1700

Data Index: 882125 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 3.8902. Min Range: -3.8902

Max Act: 3.7526. Min Act: -0.1700

Data Index: 733029 (C4 (Web Text))

Max Activating Token Index: 564

Text #11

Max Range: 3.8902. Min Range: -3.8902

Max Act: 3.7561. Min Act: -0.1700

Data Index: 1297694 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 3.8902. Min Range: -3.8902

Max Act: 3.7270. Min Act: -0.1700

Data Index: 709395 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 3.8902. Min Range: -3.8902

Max Act: 3.7285. Min Act: -0.1700

Data Index: 843623 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 3.8902. Min Range: -3.8902

Max Act: 3.7348. Min Act: -0.1700

Data Index: 1292669 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 3.8902. Min Range: -3.8902

Max Act: 3.6989. Min Act: -0.1700

Data Index: 1303654 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 3.8902. Min Range: -3.8902

Max Act: 3.7119. Min Act: -0.1700

Data Index: 970320 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 3.8902. Min Range: -3.8902

Max Act: 3.7173. Min Act: -0.1700

Data Index: 250677 (C4 (Web Text))

Max Activating Token Index: 298

Text #18

Max Range: 3.8902. Min Range: -3.8902

Max Act: 3.7201. Min Act: -0.1700

Data Index: 847477 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 3.8902. Min Range: -3.8902

Max Act: 3.6959. Min Act: -0.1700

Data Index: 531436 (C4 (Web Text))

Max Activating Token Index: 185