Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3186 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2855. Min Range: -5.2855
Max Act: 5.2855. Min Act: -0.1700
Data Index: 8804495 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2855. Min Range: -5.2855
Max Act: 5.2543. Min Act: -0.1700
Data Index: 8703255 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2855. Min Range: -5.2855
Max Act: 5.2543. Min Act: -0.1700
Data Index: 854133 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2855. Min Range: -5.2855
Max Act: 5.2855. Min Act: -0.1700
Data Index: 3644926 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2855. Min Range: -5.2855
Max Act: 5.2230. Min Act: -0.1700
Data Index: 5870304 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2855. Min Range: -5.2855
Max Act: 5.2230. Min Act: -0.1700
Data Index: 1074561 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2855. Min Range: -5.2855
Max Act: 5.1918. Min Act: -0.1700
Data Index: 7613855 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2855. Min Range: -5.2855
Max Act: 5.1918. Min Act: -0.1700
Data Index: 919950 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2855. Min Range: -5.2855
Max Act: 5.1918. Min Act: -0.1700
Data Index: 4632501 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2855. Min Range: -5.2855
Max Act: 5.1918. Min Act: -0.1700
Data Index: 6559950 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2855. Min Range: -5.2855
Max Act: 5.1918. Min Act: -0.1700
Data Index: 6529917 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2855. Min Range: -5.2855
Max Act: 5.1918. Min Act: -0.1700
Data Index: 6512948 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2855. Min Range: -5.2855
Max Act: 5.2230. Min Act: -0.1700
Data Index: 3443599 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2855. Min Range: -5.2855
Max Act: 5.1605. Min Act: -0.1699
Data Index: 6859797 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2855. Min Range: -5.2855
Max Act: 5.1605. Min Act: -0.1700
Data Index: 6143851 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2855. Min Range: -5.2855
Max Act: 5.1605. Min Act: -0.1700
Data Index: 3796751 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2855. Min Range: -5.2855
Max Act: 5.1605. Min Act: -0.1700
Data Index: 2552622 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2855. Min Range: -5.2855
Max Act: 5.1293. Min Act: -0.1700
Data Index: 6038508 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2855. Min Range: -5.2855
Max Act: 5.1605. Min Act: -0.1700
Data Index: 2648273 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2855. Min Range: -5.2855
Max Act: 5.1605. Min Act: -0.1700
Data Index: 570521 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #19