Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 697 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.7739. Min Act: -0.1700
Data Index: 5385446 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.6487. Min Act: -0.1700
Data Index: 945896 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.6644. Min Act: -0.1700
Data Index: 4823356 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.6018. Min Act: -0.1700
Data Index: 760908 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.5392. Min Act: -0.1700
Data Index: 7565539 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.5392. Min Act: -0.1700
Data Index: 5028826 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.5392. Min Act: -0.1700
Data Index: 6958817 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.5392. Min Act: -0.1700
Data Index: 2884089 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.4295. Min Act: -0.1700
Data Index: 1611257 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.4295. Min Act: -0.1700
Data Index: 2465428 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.4295. Min Act: -0.1700
Data Index: 5041128 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.4138. Min Act: -0.1700
Data Index: 1723237 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.4138. Min Act: -0.1700
Data Index: 7169190 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.4138. Min Act: -0.1700
Data Index: 1470153 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.3825. Min Act: -0.1700
Data Index: 6286227 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.3982. Min Act: -0.1700
Data Index: 3076662 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.3825. Min Act: -0.1700
Data Index: 6243798 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.3825. Min Act: -0.1700
Data Index: 3445582 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.3982. Min Act: -0.1700
Data Index: 8094494 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.3982. Min Act: -0.1700
Data Index: 3969489 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19