Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3564 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1749. Min Range: -7.1749
Max Act: 7.1749. Min Act: -0.1700
Data Index: 6015587 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1749. Min Range: -7.1749
Max Act: 7.0187. Min Act: -0.1700
Data Index: 1159942 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1749. Min Range: -7.1749
Max Act: 6.9874. Min Act: -0.1700
Data Index: 7979588 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1749. Min Range: -7.1749
Max Act: 6.8312. Min Act: -0.1700
Data Index: 3633862 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1749. Min Range: -7.1749
Max Act: 6.8624. Min Act: -0.1700
Data Index: 3693854 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1749. Min Range: -7.1749
Max Act: 6.7999. Min Act: -0.1700
Data Index: 349621 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1749. Min Range: -7.1749
Max Act: 6.7374. Min Act: -0.1700
Data Index: 6390149 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1749. Min Range: -7.1749
Max Act: 6.7687. Min Act: -0.1700
Data Index: 7483661 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1749. Min Range: -7.1749
Max Act: 6.7374. Min Act: -0.1700
Data Index: 7773271 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1749. Min Range: -7.1749
Max Act: 6.7374. Min Act: -0.1700
Data Index: 8659152 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1749. Min Range: -7.1749
Max Act: 6.6437. Min Act: -0.1700
Data Index: 5215008 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1749. Min Range: -7.1749
Max Act: 6.6124. Min Act: -0.1700
Data Index: 2511584 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1749. Min Range: -7.1749
Max Act: 6.6124. Min Act: -0.1700
Data Index: 7655760 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1749. Min Range: -7.1749
Max Act: 6.6124. Min Act: -0.1700
Data Index: 2227663 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1749. Min Range: -7.1749
Max Act: 6.5812. Min Act: -0.1700
Data Index: 8084233 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1749. Min Range: -7.1749
Max Act: 6.5812. Min Act: -0.1700
Data Index: 4090285 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1749. Min Range: -7.1749
Max Act: 6.5812. Min Act: -0.1700
Data Index: 5485874 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1749. Min Range: -7.1749
Max Act: 6.5812. Min Act: -0.1700
Data Index: 7223707 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1749. Min Range: -7.1749
Max Act: 6.5499. Min Act: -0.1700
Data Index: 6345066 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1749. Min Range: -7.1749
Max Act: 6.5812. Min Act: -0.1700
Data Index: 759543 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19