Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 573 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2335. Min Range: -5.2335
Max Act: 5.2335. Min Act: -0.1700
Data Index: 3201703 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2335. Min Range: -5.2335
Max Act: 5.1085. Min Act: -0.1700
Data Index: 7165893 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2335. Min Range: -5.2335
Max Act: 5.1085. Min Act: -0.1700
Data Index: 6195778 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2335. Min Range: -5.2335
Max Act: 5.0460. Min Act: -0.1700
Data Index: 5552027 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2335. Min Range: -5.2335
Max Act: 5.0148. Min Act: -0.1700
Data Index: 6680884 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2335. Min Range: -5.2335
Max Act: 4.9835. Min Act: -0.1700
Data Index: 7493611 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2335. Min Range: -5.2335
Max Act: 4.9523. Min Act: -0.1700
Data Index: 6651583 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2335. Min Range: -5.2335
Max Act: 4.9523. Min Act: -0.1700
Data Index: 3050642 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2335. Min Range: -5.2335
Max Act: 4.9210. Min Act: -0.1700
Data Index: 4467066 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2335. Min Range: -5.2335
Max Act: 4.9523. Min Act: -0.1700
Data Index: 7584732 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2335. Min Range: -5.2335
Max Act: 4.8898. Min Act: -0.1700
Data Index: 2558606 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2335. Min Range: -5.2335
Max Act: 4.8898. Min Act: -0.1700
Data Index: 6231462 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2335. Min Range: -5.2335
Max Act: 4.8273. Min Act: -0.1700
Data Index: 2494117 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2335. Min Range: -5.2335
Max Act: 4.7960. Min Act: -0.1700
Data Index: 1440175 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2335. Min Range: -5.2335
Max Act: 4.7648. Min Act: -0.1700
Data Index: 7104302 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2335. Min Range: -5.2335
Max Act: 4.7648. Min Act: -0.1700
Data Index: 4467068 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2335. Min Range: -5.2335
Max Act: 4.7335. Min Act: -0.1700
Data Index: 3964247 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2335. Min Range: -5.2335
Max Act: 4.7648. Min Act: -0.1700
Data Index: 6377439 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2335. Min Range: -5.2335
Max Act: 4.7023. Min Act: -0.1700
Data Index: 1045220 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2335. Min Range: -5.2335
Max Act: 4.7023. Min Act: -0.1700
Data Index: 3448395 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19