Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3560 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8827. Min Range: -4.8827
Max Act: 4.8827. Min Act: -0.1700
Data Index: 3424395 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8827. Min Range: -4.8827
Max Act: 4.7265. Min Act: -0.1700
Data Index: 3527333 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8827. Min Range: -4.8827
Max Act: 4.6327. Min Act: -0.1700
Data Index: 109153 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8827. Min Range: -4.8827
Max Act: 4.6014. Min Act: -0.1700
Data Index: 3349318 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8827. Min Range: -4.8827
Max Act: 4.5389. Min Act: -0.1700
Data Index: 5045744 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8827. Min Range: -4.8827
Max Act: 4.5389. Min Act: -0.1700
Data Index: 8355242 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8827. Min Range: -4.8827
Max Act: 4.5077. Min Act: -0.1700
Data Index: 5428134 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8827. Min Range: -4.8827
Max Act: 4.4764. Min Act: -0.1700
Data Index: 6956484 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8827. Min Range: -4.8827
Max Act: 4.4764. Min Act: -0.1700
Data Index: 1233493 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8827. Min Range: -4.8827
Max Act: 4.4452. Min Act: -0.1700
Data Index: 3907091 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8827. Min Range: -4.8827
Max Act: 4.4452. Min Act: -0.1700
Data Index: 2301805 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8827. Min Range: -4.8827
Max Act: 4.4139. Min Act: -0.1700
Data Index: 109150 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8827. Min Range: -4.8827
Max Act: 4.4139. Min Act: -0.1700
Data Index: 4319830 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8827. Min Range: -4.8827
Max Act: 4.4139. Min Act: -0.1700
Data Index: 8106383 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8827. Min Range: -4.8827
Max Act: 4.4139. Min Act: -0.1700
Data Index: 6023300 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8827. Min Range: -4.8827
Max Act: 4.4139. Min Act: -0.1700
Data Index: 2627963 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8827. Min Range: -4.8827
Max Act: 4.3827. Min Act: -0.1700
Data Index: 6486664 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8827. Min Range: -4.8827
Max Act: 4.3827. Min Act: -0.1700
Data Index: 7680157 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8827. Min Range: -4.8827
Max Act: 4.3827. Min Act: -0.1700
Data Index: 2042318 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8827. Min Range: -4.8827
Max Act: 4.3827. Min Act: -0.1700
Data Index: 70719 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19