Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1827 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2666. Min Range: -4.2666
Max Act: 4.2666. Min Act: -0.1700
Data Index: 1943270 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2666. Min Range: -4.2666
Max Act: 3.8915. Min Act: -0.1700
Data Index: 5694953 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2666. Min Range: -4.2666
Max Act: 3.8290. Min Act: -0.1700
Data Index: 8009260 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2666. Min Range: -4.2666
Max Act: 3.8290. Min Act: -0.1700
Data Index: 5689082 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2666. Min Range: -4.2666
Max Act: 3.7977. Min Act: -0.1700
Data Index: 6827985 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2666. Min Range: -4.2666
Max Act: 3.8290. Min Act: -0.1700
Data Index: 6032729 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2666. Min Range: -4.2666
Max Act: 3.7664. Min Act: -0.1700
Data Index: 3324716 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2666. Min Range: -4.2666
Max Act: 3.7351. Min Act: -0.1700
Data Index: 3465216 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2666. Min Range: -4.2666
Max Act: 3.7664. Min Act: -0.1700
Data Index: 3465217 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2666. Min Range: -4.2666
Max Act: 3.7664. Min Act: -0.1700
Data Index: 3421048 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2666. Min Range: -4.2666
Max Act: 3.7351. Min Act: -0.1700
Data Index: 6796542 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2666. Min Range: -4.2666
Max Act: 3.7351. Min Act: -0.1700
Data Index: 1599275 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2666. Min Range: -4.2666
Max Act: 3.7351. Min Act: -0.1700
Data Index: 8278317 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2666. Min Range: -4.2666
Max Act: 3.7351. Min Act: -0.1700
Data Index: 2270135 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2666. Min Range: -4.2666
Max Act: 3.7039. Min Act: -0.1700
Data Index: 6032730 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2666. Min Range: -4.2666
Max Act: 3.7351. Min Act: -0.1700
Data Index: 6827984 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2666. Min Range: -4.2666
Max Act: 3.7351. Min Act: -0.1700
Data Index: 433424 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2666. Min Range: -4.2666
Max Act: 3.7039. Min Act: -0.1700
Data Index: 4136954 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2666. Min Range: -4.2666
Max Act: 3.7039. Min Act: -0.1700
Data Index: 2441837 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2666. Min Range: -4.2666
Max Act: 3.7351. Min Act: -0.1700
Data Index: 4136955 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #19