Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2805 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5328. Min Range: -5.5328
Max Act: 5.5328. Min Act: -0.1700
Data Index: 8801652 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5328. Min Range: -5.5328
Max Act: 5.1890. Min Act: -0.1700
Data Index: 3709952 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5328. Min Range: -5.5328
Max Act: 5.1890. Min Act: -0.1700
Data Index: 6839266 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5328. Min Range: -5.5328
Max Act: 5.1265. Min Act: -0.1700
Data Index: 6470427 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5328. Min Range: -5.5328
Max Act: 5.1265. Min Act: -0.1700
Data Index: 6566921 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5328. Min Range: -5.5328
Max Act: 5.0953. Min Act: -0.1700
Data Index: 1440215 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5328. Min Range: -5.5328
Max Act: 5.0640. Min Act: -0.1700
Data Index: 1067595 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5328. Min Range: -5.5328
Max Act: 5.0640. Min Act: -0.1700
Data Index: 5456276 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5328. Min Range: -5.5328
Max Act: 5.0640. Min Act: -0.1700
Data Index: 5485807 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5328. Min Range: -5.5328
Max Act: 5.0953. Min Act: -0.1700
Data Index: 6079530 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5328. Min Range: -5.5328
Max Act: 5.0328. Min Act: -0.1700
Data Index: 2667754 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5328. Min Range: -5.5328
Max Act: 5.0328. Min Act: -0.1700
Data Index: 7856911 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5328. Min Range: -5.5328
Max Act: 5.0640. Min Act: -0.1700
Data Index: 8146732 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5328. Min Range: -5.5328
Max Act: 5.0015. Min Act: -0.1700
Data Index: 8770453 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5328. Min Range: -5.5328
Max Act: 4.9703. Min Act: -0.1700
Data Index: 77964 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5328. Min Range: -5.5328
Max Act: 5.0015. Min Act: -0.1700
Data Index: 6132086 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5328. Min Range: -5.5328
Max Act: 5.0015. Min Act: -0.1700
Data Index: 8294943 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5328. Min Range: -5.5328
Max Act: 4.9703. Min Act: -0.1700
Data Index: 6704548 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5328. Min Range: -5.5328
Max Act: 4.9703. Min Act: -0.1700
Data Index: 4401304 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5328. Min Range: -5.5328
Max Act: 4.9703. Min Act: -0.1700
Data Index: 3813316 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19