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

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

Neuron 548 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: 4.3591. Min Range: -4.3591

Max Act: 4.3591. Min Act: -0.1700

Data Index: 1201438 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 4.3591. Min Range: -4.3591

Max Act: 4.2469. Min Act: -0.1700

Data Index: 1046771 (C4 (Web Text))

Max Activating Token Index: 460

Text #2

Max Range: 4.3591. Min Range: -4.3591

Max Act: 4.2604. Min Act: -0.1700

Data Index: 729258 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 4.3591. Min Range: -4.3591

Max Act: 4.1772. Min Act: -0.1700

Data Index: 253168 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 4.3591. Min Range: -4.3591

Max Act: 4.1886. Min Act: -0.1700

Data Index: 142875 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 4.3591. Min Range: -4.3591

Max Act: 4.1689. Min Act: -0.1700

Data Index: 1046484 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 4.3591. Min Range: -4.3591

Max Act: 4.1497. Min Act: -0.1700

Data Index: 545800 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 4.3591. Min Range: -4.3591

Max Act: 4.1779. Min Act: -0.1700

Data Index: 1020160 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 4.3591. Min Range: -4.3591

Max Act: 4.2041. Min Act: -0.1700

Data Index: 754558 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 4.3591. Min Range: -4.3591

Max Act: 4.1958. Min Act: -0.1700

Data Index: 1145599 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 4.3591. Min Range: -4.3591

Max Act: 4.1948. Min Act: -0.1700

Data Index: 69330 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 4.3591. Min Range: -4.3591

Max Act: 4.2412. Min Act: -0.1700

Data Index: 1217276 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 4.3591. Min Range: -4.3591

Max Act: 4.1518. Min Act: -0.1700

Data Index: 1584047 (Python Code)

Max Activating Token Index: 397

Text #13

Max Range: 4.3591. Min Range: -4.3591

Max Act: 4.1160. Min Act: -0.1700

Data Index: 1057591 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 4.3591. Min Range: -4.3591

Max Act: 4.1776. Min Act: -0.1700

Data Index: 557462 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 4.3591. Min Range: -4.3591

Max Act: 4.1480. Min Act: -0.1700

Data Index: 956147 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 4.3591. Min Range: -4.3591

Max Act: 4.1665. Min Act: -0.1700

Data Index: 1031198 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 4.3591. Min Range: -4.3591

Max Act: 4.1426. Min Act: -0.1700

Data Index: 733613 (C4 (Web Text))

Max Activating Token Index: 834

Text #18

Max Range: 4.3591. Min Range: -4.3591

Max Act: 4.1711. Min Act: -0.1700

Data Index: 996659 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 4.3591. Min Range: -4.3591

Max Act: 4.1804. Min Act: -0.1700

Data Index: 198795 (C4 (Web Text))

Max Activating Token Index: 592