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

Dataset: Open Web Text

Neuron 2296 in Layer 6

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: 3.8492. Min Range: -3.8492

Max Act: 3.8492. Min Act: -0.1700

Data Index: 3848931 (Open Web Text)

Max Activating Token Index: 289

Text #1

Max Range: 3.8492. Min Range: -3.8492

Max Act: 3.7800. Min Act: -0.1700

Data Index: 3319719 (Open Web Text)

Max Activating Token Index: 454

Text #2

Max Range: 3.8492. Min Range: -3.8492

Max Act: 3.7374. Min Act: -0.1700

Data Index: 6775565 (Open Web Text)

Max Activating Token Index: 854

Text #3

Max Range: 3.8492. Min Range: -3.8492

Max Act: 3.7497. Min Act: -0.1700

Data Index: 3851069 (Open Web Text)

Max Activating Token Index: 639

Text #4

Max Range: 3.8492. Min Range: -3.8492

Max Act: 3.7385. Min Act: -0.1700

Data Index: 1022975 (Open Web Text)

Max Activating Token Index: 140

Text #5

Max Range: 3.8492. Min Range: -3.8492

Max Act: 3.7619. Min Act: -0.1700

Data Index: 4651106 (Open Web Text)

Max Activating Token Index: 498

Text #6

Max Range: 3.8492. Min Range: -3.8492

Max Act: 3.7081. Min Act: -0.1700

Data Index: 749731 (Open Web Text)

Max Activating Token Index: 601

Text #7

Max Range: 3.8492. Min Range: -3.8492

Max Act: 3.7147. Min Act: -0.1700

Data Index: 8031548 (Open Web Text)

Max Activating Token Index: 718

Text #8

Max Range: 3.8492. Min Range: -3.8492

Max Act: 3.7014. Min Act: -0.1700

Data Index: 7740145 (Open Web Text)

Max Activating Token Index: 223

Text #9

Max Range: 3.8492. Min Range: -3.8492

Max Act: 3.6764. Min Act: -0.1700

Data Index: 1353385 (Open Web Text)

Max Activating Token Index: 517

Text #10

Max Range: 3.8492. Min Range: -3.8492

Max Act: 3.6794. Min Act: -0.1700

Data Index: 8246662 (Open Web Text)

Max Activating Token Index: 889

Text #11

Max Range: 3.8492. Min Range: -3.8492

Max Act: 3.6847. Min Act: -0.1700

Data Index: 8781446 (Open Web Text)

Max Activating Token Index: 163

Text #12

Max Range: 3.8492. Min Range: -3.8492

Max Act: 3.6739. Min Act: -0.1700

Data Index: 3953612 (Open Web Text)

Max Activating Token Index: 772

Text #13

Max Range: 3.8492. Min Range: -3.8492

Max Act: 3.6946. Min Act: -0.1700

Data Index: 2240251 (Open Web Text)

Max Activating Token Index: 754

Text #14

Max Range: 3.8492. Min Range: -3.8492

Max Act: 3.6985. Min Act: -0.1700

Data Index: 4907724 (Open Web Text)

Max Activating Token Index: 568

Text #15

Max Range: 3.8492. Min Range: -3.8492

Max Act: 3.6763. Min Act: -0.1700

Data Index: 3790802 (Open Web Text)

Max Activating Token Index: 643

Text #16

Max Range: 3.8492. Min Range: -3.8492

Max Act: 3.6394. Min Act: -0.1700

Data Index: 4411486 (Open Web Text)

Max Activating Token Index: 790

Text #17

Max Range: 3.8492. Min Range: -3.8492

Max Act: 3.6524. Min Act: -0.1700

Data Index: 2628316 (Open Web Text)

Max Activating Token Index: 481

Text #18

Max Range: 3.8492. Min Range: -3.8492

Max Act: 3.6478. Min Act: -0.1700

Data Index: 3487932 (Open Web Text)

Max Activating Token Index: 151

Text #19

Max Range: 3.8492. Min Range: -3.8492

Max Act: 3.6311. Min Act: -0.1700

Data Index: 2069453 (Open Web Text)

Max Activating Token Index: 775