Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3628 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4598. Min Range: -6.4598
Max Act: 6.4598. Min Act: -0.1700
Data Index: 1040156 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4598. Min Range: -6.4598
Max Act: 6.3035. Min Act: -0.1700
Data Index: 8279039 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4598. Min Range: -6.4598
Max Act: 6.2098. Min Act: -0.1700
Data Index: 2638956 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4598. Min Range: -6.4598
Max Act: 6.1785. Min Act: -0.1700
Data Index: 7943004 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4598. Min Range: -6.4598
Max Act: 6.0848. Min Act: -0.1700
Data Index: 7832753 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4598. Min Range: -6.4598
Max Act: 6.0223. Min Act: -0.1700
Data Index: 6072871 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4598. Min Range: -6.4598
Max Act: 6.0223. Min Act: -0.1700
Data Index: 4961342 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4598. Min Range: -6.4598
Max Act: 5.9910. Min Act: -0.1700
Data Index: 1796676 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4598. Min Range: -6.4598
Max Act: 6.0223. Min Act: -0.1700
Data Index: 10964 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4598. Min Range: -6.4598
Max Act: 5.9285. Min Act: -0.1700
Data Index: 6283983 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4598. Min Range: -6.4598
Max Act: 5.8973. Min Act: -0.1700
Data Index: 2596203 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4598. Min Range: -6.4598
Max Act: 5.8660. Min Act: -0.1700
Data Index: 7906578 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4598. Min Range: -6.4598
Max Act: 5.8660. Min Act: -0.1700
Data Index: 51787 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4598. Min Range: -6.4598
Max Act: 5.8348. Min Act: -0.1700
Data Index: 5814630 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4598. Min Range: -6.4598
Max Act: 5.8035. Min Act: -0.1700
Data Index: 6019210 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4598. Min Range: -6.4598
Max Act: 5.8035. Min Act: -0.1700
Data Index: 2702726 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4598. Min Range: -6.4598
Max Act: 5.7410. Min Act: -0.1700
Data Index: 4605823 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4598. Min Range: -6.4598
Max Act: 5.7723. Min Act: -0.1700
Data Index: 7866847 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4598. Min Range: -6.4598
Max Act: 5.7410. Min Act: -0.1700
Data Index: 5132413 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4598. Min Range: -6.4598
Max Act: 5.7098. Min Act: -0.1700
Data Index: 7718368 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #19