Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 690 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.8466. Min Range: -5.8466

Max Act: 5.8153. Min Act: -0.1700

Data Index: 362708 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 5.8466. Min Range: -5.8466

Max Act: 5.8466. Min Act: -0.1700

Data Index: 526084 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 5.8466. Min Range: -5.8466

Max Act: 5.6278. Min Act: -0.1700

Data Index: 1297837 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 5.8466. Min Range: -5.8466

Max Act: 5.5966. Min Act: -0.1700

Data Index: 400061 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 5.8466. Min Range: -5.8466

Max Act: 5.5966. Min Act: -0.1700

Data Index: 216092 (C4 (Web Text))

Max Activating Token Index: 603

Text #5

Max Range: 5.8466. Min Range: -5.8466

Max Act: 5.6278. Min Act: -0.1700

Data Index: 737283 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 5.8466. Min Range: -5.8466

Max Act: 5.6278. Min Act: -0.1700

Data Index: 403390 (C4 (Web Text))

Max Activating Token Index: 495

Text #7

Max Range: 5.8466. Min Range: -5.8466

Max Act: 5.5966. Min Act: -0.1700

Data Index: 871724 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 5.8466. Min Range: -5.8466

Max Act: 5.5653. Min Act: -0.1700

Data Index: 553628 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 5.8466. Min Range: -5.8466

Max Act: 5.5653. Min Act: -0.1700

Data Index: 626467 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 5.8466. Min Range: -5.8466

Max Act: 5.4716. Min Act: -0.1700

Data Index: 776073 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 5.8466. Min Range: -5.8466

Max Act: 5.5341. Min Act: -0.1700

Data Index: 642682 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 5.8466. Min Range: -5.8466

Max Act: 5.5653. Min Act: -0.1700

Data Index: 975420 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 5.8466. Min Range: -5.8466

Max Act: 5.4716. Min Act: -0.1700

Data Index: 406748 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 5.8466. Min Range: -5.8466

Max Act: 5.4716. Min Act: -0.1700

Data Index: 1348564 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 5.8466. Min Range: -5.8466

Max Act: 5.4091. Min Act: -0.1700

Data Index: 357064 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 5.8466. Min Range: -5.8466

Max Act: 5.5028. Min Act: -0.1700

Data Index: 504527 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 5.8466. Min Range: -5.8466

Max Act: 5.5028. Min Act: -0.1700

Data Index: 476103 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 5.8466. Min Range: -5.8466

Max Act: 5.5341. Min Act: -0.1700

Data Index: 952239 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 5.8466. Min Range: -5.8466

Max Act: 5.4403. Min Act: -0.1700

Data Index: 494183 (C4 (Web Text))

Max Activating Token Index: 364