Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 671 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 5.1230. Min Range: -5.1230

Max Act: 5.1230. Min Act: -0.1700

Data Index: 2495156 (Open Web Text)

Max Activating Token Index: 285

Text #1

Max Range: 5.1230. Min Range: -5.1230

Max Act: 5.0561. Min Act: -0.1700

Data Index: 8007576 (Open Web Text)

Max Activating Token Index: 1014

Text #2

Max Range: 5.1230. Min Range: -5.1230

Max Act: 4.9665. Min Act: -0.1700

Data Index: 8438543 (Open Web Text)

Max Activating Token Index: 666

Text #3

Max Range: 5.1230. Min Range: -5.1230

Max Act: 5.0197. Min Act: -0.1700

Data Index: 6150853 (Open Web Text)

Max Activating Token Index: 685

Text #4

Max Range: 5.1230. Min Range: -5.1230

Max Act: 4.9672. Min Act: -0.1700

Data Index: 4450666 (Open Web Text)

Max Activating Token Index: 743

Text #5

Max Range: 5.1230. Min Range: -5.1230

Max Act: 4.9306. Min Act: -0.1700

Data Index: 7236090 (Open Web Text)

Max Activating Token Index: 739

Text #6

Max Range: 5.1230. Min Range: -5.1230

Max Act: 4.9018. Min Act: -0.1700

Data Index: 2799116 (Open Web Text)

Max Activating Token Index: 187

Text #7

Max Range: 5.1230. Min Range: -5.1230

Max Act: 4.8294. Min Act: -0.1700

Data Index: 8793004 (Open Web Text)

Max Activating Token Index: 509

Text #8

Max Range: 5.1230. Min Range: -5.1230

Max Act: 4.7738. Min Act: -0.1700

Data Index: 6170891 (Open Web Text)

Max Activating Token Index: 960

Text #9

Max Range: 5.1230. Min Range: -5.1230

Max Act: 4.7753. Min Act: -0.1700

Data Index: 1083602 (Open Web Text)

Max Activating Token Index: 649

Text #10

Max Range: 5.1230. Min Range: -5.1230

Max Act: 4.8090. Min Act: -0.1700

Data Index: 2709610 (Open Web Text)

Max Activating Token Index: 433

Text #11

Max Range: 5.1230. Min Range: -5.1230

Max Act: 4.7718. Min Act: -0.1700

Data Index: 3591395 (Open Web Text)

Max Activating Token Index: 820

Text #12

Max Range: 5.1230. Min Range: -5.1230

Max Act: 4.7707. Min Act: -0.1700

Data Index: 5085314 (Open Web Text)

Max Activating Token Index: 384

Text #13

Max Range: 5.1230. Min Range: -5.1230

Max Act: 4.6843. Min Act: -0.1700

Data Index: 2876471 (Open Web Text)

Max Activating Token Index: 867

Text #14

Max Range: 5.1230. Min Range: -5.1230

Max Act: 4.7708. Min Act: -0.1700

Data Index: 4026934 (Open Web Text)

Max Activating Token Index: 443

Text #15

Max Range: 5.1230. Min Range: -5.1230

Max Act: 4.6998. Min Act: -0.1700

Data Index: 7878977 (Open Web Text)

Max Activating Token Index: 389

Text #16

Max Range: 5.1230. Min Range: -5.1230

Max Act: 4.6620. Min Act: -0.1700

Data Index: 1141782 (Open Web Text)

Max Activating Token Index: 723

Text #17

Max Range: 5.1230. Min Range: -5.1230

Max Act: 4.6727. Min Act: -0.1700

Data Index: 16676 (Open Web Text)

Max Activating Token Index: 352

Text #18

Max Range: 5.1230. Min Range: -5.1230

Max Act: 4.7217. Min Act: -0.1700

Data Index: 8323152 (Open Web Text)

Max Activating Token Index: 98

Text #19

Max Range: 5.1230. Min Range: -5.1230

Max Act: 4.7418. Min Act: -0.1700

Data Index: 3154549 (Open Web Text)

Max Activating Token Index: 601