Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3896 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0848. Min Range: -6.0848
Max Act: 6.0848. Min Act: -0.1700
Data Index: 5360847 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0848. Min Range: -6.0848
Max Act: 6.0223. Min Act: -0.1700
Data Index: 6866369 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0848. Min Range: -6.0848
Max Act: 5.9910. Min Act: -0.1700
Data Index: 5013820 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0848. Min Range: -6.0848
Max Act: 5.9598. Min Act: -0.1700
Data Index: 2691237 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0848. Min Range: -6.0848
Max Act: 5.9598. Min Act: -0.1700
Data Index: 7319209 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0848. Min Range: -6.0848
Max Act: 5.8660. Min Act: -0.1700
Data Index: 362888 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0848. Min Range: -6.0848
Max Act: 5.8660. Min Act: -0.1700
Data Index: 4432975 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0848. Min Range: -6.0848
Max Act: 5.8348. Min Act: -0.1700
Data Index: 541021 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0848. Min Range: -6.0848
Max Act: 5.7410. Min Act: -0.1700
Data Index: 8275503 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0848. Min Range: -6.0848
Max Act: 5.7098. Min Act: -0.1700
Data Index: 8591452 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0848. Min Range: -6.0848
Max Act: 5.7410. Min Act: -0.1700
Data Index: 7371831 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0848. Min Range: -6.0848
Max Act: 5.7098. Min Act: -0.1700
Data Index: 8812318 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0848. Min Range: -6.0848
Max Act: 5.7098. Min Act: -0.1700
Data Index: 2046687 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0848. Min Range: -6.0848
Max Act: 5.7098. Min Act: -0.1700
Data Index: 7141972 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0848. Min Range: -6.0848
Max Act: 5.7098. Min Act: -0.1700
Data Index: 5085085 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0848. Min Range: -6.0848
Max Act: 5.7098. Min Act: -0.1700
Data Index: 3389727 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0848. Min Range: -6.0848
Max Act: 5.6785. Min Act: -0.1700
Data Index: 8210676 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0848. Min Range: -6.0848
Max Act: 5.6473. Min Act: -0.1700
Data Index: 351600 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0848. Min Range: -6.0848
Max Act: 5.6473. Min Act: -0.1700
Data Index: 4300546 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0848. Min Range: -6.0848
Max Act: 5.6473. Min Act: -0.1700
Data Index: 1220789 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19