Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1798 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8618. Min Range: -6.8618
Max Act: 6.8618. Min Act: -0.1700
Data Index: 5848320 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8618. Min Range: -6.8618
Max Act: 6.8306. Min Act: -0.1700
Data Index: 5782368 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8618. Min Range: -6.8618
Max Act: 6.7681. Min Act: -0.1700
Data Index: 4519814 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8618. Min Range: -6.8618
Max Act: 6.5181. Min Act: -0.1700
Data Index: 7339768 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8618. Min Range: -6.8618
Max Act: 6.5181. Min Act: -0.1700
Data Index: 2643071 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8618. Min Range: -6.8618
Max Act: 6.4556. Min Act: -0.1700
Data Index: 8804700 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8618. Min Range: -6.8618
Max Act: 6.3931. Min Act: -0.1700
Data Index: 8607139 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8618. Min Range: -6.8618
Max Act: 6.2993. Min Act: -0.1700
Data Index: 2649872 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8618. Min Range: -6.8618
Max Act: 6.2993. Min Act: -0.1700
Data Index: 4231160 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8618. Min Range: -6.8618
Max Act: 6.2993. Min Act: -0.1700
Data Index: 3849128 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8618. Min Range: -6.8618
Max Act: 6.2681. Min Act: -0.1700
Data Index: 8238636 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8618. Min Range: -6.8618
Max Act: 6.2993. Min Act: -0.1700
Data Index: 6201516 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8618. Min Range: -6.8618
Max Act: 6.2681. Min Act: -0.1700
Data Index: 4381368 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8618. Min Range: -6.8618
Max Act: 6.2056. Min Act: -0.1700
Data Index: 8656662 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8618. Min Range: -6.8618
Max Act: 6.2368. Min Act: -0.1700
Data Index: 4462105 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8618. Min Range: -6.8618
Max Act: 6.2056. Min Act: -0.1700
Data Index: 3807868 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8618. Min Range: -6.8618
Max Act: 6.2056. Min Act: -0.1700
Data Index: 7540856 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8618. Min Range: -6.8618
Max Act: 6.1743. Min Act: -0.1700
Data Index: 6333259 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8618. Min Range: -6.8618
Max Act: 6.1743. Min Act: -0.1700
Data Index: 4074216 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8618. Min Range: -6.8618
Max Act: 6.1431. Min Act: -0.1700
Data Index: 3563357 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #19