Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2595 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.9092. Min Act: -0.1700
Data Index: 2963772 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.8779. Min Act: -0.1700
Data Index: 2733772 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.8154. Min Act: -0.1700
Data Index: 3053735 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.7529. Min Act: -0.1700
Data Index: 4110787 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.7217. Min Act: -0.1700
Data Index: 7275878 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.7217. Min Act: -0.1700
Data Index: 4979988 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.7217. Min Act: -0.1700
Data Index: 4687137 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.7217. Min Act: -0.1700
Data Index: 5578729 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.7217. Min Act: -0.1700
Data Index: 3093679 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.6904. Min Act: -0.1700
Data Index: 5843143 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.6904. Min Act: -0.1700
Data Index: 338661 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.6904. Min Act: -0.1700
Data Index: 2657925 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.7217. Min Act: -0.1700
Data Index: 3850505 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.6592. Min Act: -0.1700
Data Index: 3805629 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.6592. Min Act: -0.1700
Data Index: 1813901 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.6592. Min Act: -0.1700
Data Index: 4618133 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.6904. Min Act: -0.1700
Data Index: 449994 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.6279. Min Act: -0.1700
Data Index: 7755615 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.6592. Min Act: -0.1700
Data Index: 7003960 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.6279. Min Act: -0.1700
Data Index: 6687095 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19