Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3313 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8952. Min Range: -3.8952
Max Act: 3.8952. Min Act: -0.1700
Data Index: 8576792 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8952. Min Range: -3.8952
Max Act: 3.8640. Min Act: -0.1700
Data Index: 816451 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8952. Min Range: -3.8952
Max Act: 3.7076. Min Act: -0.1700
Data Index: 4296600 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8952. Min Range: -3.8952
Max Act: 3.7076. Min Act: -0.1700
Data Index: 1724187 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8952. Min Range: -3.8952
Max Act: 3.6763. Min Act: -0.1700
Data Index: 7674131 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8952. Min Range: -3.8952
Max Act: 3.6763. Min Act: -0.1700
Data Index: 7257589 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8952. Min Range: -3.8952
Max Act: 3.6763. Min Act: -0.1700
Data Index: 80133 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8952. Min Range: -3.8952
Max Act: 3.6450. Min Act: -0.1700
Data Index: 5120308 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8952. Min Range: -3.8952
Max Act: 3.6763. Min Act: -0.1700
Data Index: 7684231 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8952. Min Range: -3.8952
Max Act: 3.6137. Min Act: -0.1700
Data Index: 7316350 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8952. Min Range: -3.8952
Max Act: 3.6137. Min Act: -0.1700
Data Index: 1149694 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8952. Min Range: -3.8952
Max Act: 3.6137. Min Act: -0.1700
Data Index: 1793947 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8952. Min Range: -3.8952
Max Act: 3.5824. Min Act: -0.1700
Data Index: 3302900 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8952. Min Range: -3.8952
Max Act: 3.5824. Min Act: -0.1700
Data Index: 1693505 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8952. Min Range: -3.8952
Max Act: 3.5824. Min Act: -0.1700
Data Index: 6849683 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8952. Min Range: -3.8952
Max Act: 3.6137. Min Act: -0.1700
Data Index: 2250040 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8952. Min Range: -3.8952
Max Act: 3.5824. Min Act: -0.1700
Data Index: 4764196 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8952. Min Range: -3.8952
Max Act: 3.5824. Min Act: -0.1700
Data Index: 8632966 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8952. Min Range: -3.8952
Max Act: 3.5824. Min Act: -0.1700
Data Index: 5950483 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8952. Min Range: -3.8952
Max Act: 3.5511. Min Act: -0.1700
Data Index: 4681432 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #19