Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3707 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5808. Min Range: -5.5808
Max Act: 5.5808. Min Act: -0.1700
Data Index: 4036261 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5808. Min Range: -5.5808
Max Act: 5.4870. Min Act: -0.1700
Data Index: 2132035 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5808. Min Range: -5.5808
Max Act: 5.3620. Min Act: -0.1700
Data Index: 6844498 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5808. Min Range: -5.5808
Max Act: 5.3620. Min Act: -0.1700
Data Index: 4026661 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5808. Min Range: -5.5808
Max Act: 5.3308. Min Act: -0.1700
Data Index: 2819756 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5808. Min Range: -5.5808
Max Act: 5.2995. Min Act: -0.1700
Data Index: 7488280 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5808. Min Range: -5.5808
Max Act: 5.2995. Min Act: -0.1700
Data Index: 265850 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5808. Min Range: -5.5808
Max Act: 5.2683. Min Act: -0.1700
Data Index: 4745311 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5808. Min Range: -5.5808
Max Act: 5.2370. Min Act: -0.1700
Data Index: 6391179 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5808. Min Range: -5.5808
Max Act: 5.2370. Min Act: -0.1700
Data Index: 7416406 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5808. Min Range: -5.5808
Max Act: 5.2370. Min Act: -0.1700
Data Index: 4311734 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5808. Min Range: -5.5808
Max Act: 5.2058. Min Act: -0.1700
Data Index: 6142346 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5808. Min Range: -5.5808
Max Act: 5.1745. Min Act: -0.1700
Data Index: 5806733 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5808. Min Range: -5.5808
Max Act: 5.2058. Min Act: -0.1700
Data Index: 621032 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5808. Min Range: -5.5808
Max Act: 5.2058. Min Act: -0.1700
Data Index: 2512447 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5808. Min Range: -5.5808
Max Act: 5.1433. Min Act: -0.1700
Data Index: 3810107 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5808. Min Range: -5.5808
Max Act: 5.1745. Min Act: -0.1700
Data Index: 3719679 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5808. Min Range: -5.5808
Max Act: 5.1433. Min Act: -0.1700
Data Index: 5677038 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5808. Min Range: -5.5808
Max Act: 5.1433. Min Act: -0.1700
Data Index: 1006559 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5808. Min Range: -5.5808
Max Act: 5.1433. Min Act: -0.1700
Data Index: 8699653 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19