Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 22 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8793. Min Range: -4.8793
Max Act: 4.8793. Min Act: -0.1700
Data Index: 8074754 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8793. Min Range: -4.8793
Max Act: 4.8481. Min Act: -0.1700
Data Index: 3172101 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8793. Min Range: -4.8793
Max Act: 4.8168. Min Act: -0.1700
Data Index: 8352720 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8793. Min Range: -4.8793
Max Act: 4.8168. Min Act: -0.1700
Data Index: 93226 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8793. Min Range: -4.8793
Max Act: 4.8168. Min Act: -0.1700
Data Index: 1065595 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8793. Min Range: -4.8793
Max Act: 4.8168. Min Act: -0.1700
Data Index: 1358426 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8793. Min Range: -4.8793
Max Act: 4.7856. Min Act: -0.1700
Data Index: 7953453 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8793. Min Range: -4.8793
Max Act: 4.7856. Min Act: -0.1700
Data Index: 8118675 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8793. Min Range: -4.8793
Max Act: 4.7856. Min Act: -0.1700
Data Index: 3828895 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8793. Min Range: -4.8793
Max Act: 4.7856. Min Act: -0.1700
Data Index: 1614987 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8793. Min Range: -4.8793
Max Act: 4.7856. Min Act: -0.1700
Data Index: 1625306 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8793. Min Range: -4.8793
Max Act: 4.7856. Min Act: -0.1700
Data Index: 5379040 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8793. Min Range: -4.8793
Max Act: 4.7543. Min Act: -0.1700
Data Index: 7653844 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8793. Min Range: -4.8793
Max Act: 4.7543. Min Act: -0.1700
Data Index: 5534653 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8793. Min Range: -4.8793
Max Act: 4.7543. Min Act: -0.1700
Data Index: 3357746 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8793. Min Range: -4.8793
Max Act: 4.7543. Min Act: -0.1700
Data Index: 5425261 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8793. Min Range: -4.8793
Max Act: 4.7543. Min Act: -0.1700
Data Index: 1913743 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8793. Min Range: -4.8793
Max Act: 4.7543. Min Act: -0.1700
Data Index: 2600805 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8793. Min Range: -4.8793
Max Act: 4.7543. Min Act: -0.1700
Data Index: 5147101 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8793. Min Range: -4.8793
Max Act: 4.7543. Min Act: -0.1700
Data Index: 4893693 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #19