Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1384 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7911. Min Range: -5.7911
Max Act: 5.7911. Min Act: -0.1700
Data Index: 1325842 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7911. Min Range: -5.7911
Max Act: 5.6973. Min Act: -0.1700
Data Index: 188627 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7911. Min Range: -5.7911
Max Act: 5.6348. Min Act: -0.1700
Data Index: 827004 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7911. Min Range: -5.7911
Max Act: 5.6036. Min Act: -0.1700
Data Index: 7715195 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7911. Min Range: -5.7911
Max Act: 5.5723. Min Act: -0.1700
Data Index: 7829436 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7911. Min Range: -5.7911
Max Act: 5.5411. Min Act: -0.1700
Data Index: 3402031 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7911. Min Range: -5.7911
Max Act: 5.4786. Min Act: -0.1700
Data Index: 6420071 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7911. Min Range: -5.7911
Max Act: 5.4786. Min Act: -0.1700
Data Index: 171713 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7911. Min Range: -5.7911
Max Act: 5.5098. Min Act: -0.1700
Data Index: 3717059 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7911. Min Range: -5.7911
Max Act: 5.4786. Min Act: -0.1700
Data Index: 7345762 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7911. Min Range: -5.7911
Max Act: 5.4786. Min Act: -0.1700
Data Index: 7813679 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7911. Min Range: -5.7911
Max Act: 5.4786. Min Act: -0.1700
Data Index: 3548736 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7911. Min Range: -5.7911
Max Act: 5.4786. Min Act: -0.1700
Data Index: 731791 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7911. Min Range: -5.7911
Max Act: 5.4473. Min Act: -0.1700
Data Index: 4512728 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7911. Min Range: -5.7911
Max Act: 5.4161. Min Act: -0.1700
Data Index: 6807065 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7911. Min Range: -5.7911
Max Act: 5.4161. Min Act: -0.1700
Data Index: 5141435 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7911. Min Range: -5.7911
Max Act: 5.4161. Min Act: -0.1700
Data Index: 6141103 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7911. Min Range: -5.7911
Max Act: 5.4473. Min Act: -0.1700
Data Index: 2815577 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7911. Min Range: -5.7911
Max Act: 5.4161. Min Act: -0.1700
Data Index: 2926231 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7911. Min Range: -5.7911
Max Act: 5.3848. Min Act: -0.1700
Data Index: 6161896 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19