Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6377 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3060. Min Range: -7.3060
Max Act: 7.3060. Min Act: -0.1700
Data Index: 7244533 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3060. Min Range: -7.3060
Max Act: 7.1185. Min Act: -0.1700
Data Index: 1477266 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3060. Min Range: -7.3060
Max Act: 7.1497. Min Act: -0.1700
Data Index: 3276237 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3060. Min Range: -7.3060
Max Act: 6.9622. Min Act: -0.1700
Data Index: 7547247 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3060. Min Range: -7.3060
Max Act: 6.8997. Min Act: -0.1700
Data Index: 7929712 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3060. Min Range: -7.3060
Max Act: 6.8685. Min Act: -0.1700
Data Index: 7101629 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3060. Min Range: -7.3060
Max Act: 6.8060. Min Act: -0.1700
Data Index: 8667235 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3060. Min Range: -7.3060
Max Act: 6.7747. Min Act: -0.1700
Data Index: 6173373 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3060. Min Range: -7.3060
Max Act: 6.7747. Min Act: -0.1700
Data Index: 604115 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3060. Min Range: -7.3060
Max Act: 6.7122. Min Act: -0.1700
Data Index: 4471471 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3060. Min Range: -7.3060
Max Act: 6.7122. Min Act: -0.1700
Data Index: 8434746 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3060. Min Range: -7.3060
Max Act: 6.7122. Min Act: -0.1700
Data Index: 419350 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3060. Min Range: -7.3060
Max Act: 6.6810. Min Act: -0.1700
Data Index: 3461416 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3060. Min Range: -7.3060
Max Act: 6.6810. Min Act: -0.1700
Data Index: 131379 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3060. Min Range: -7.3060
Max Act: 6.6497. Min Act: -0.1700
Data Index: 6173036 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3060. Min Range: -7.3060
Max Act: 6.6810. Min Act: -0.1700
Data Index: 297256 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3060. Min Range: -7.3060
Max Act: 6.6497. Min Act: -0.1700
Data Index: 3861566 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3060. Min Range: -7.3060
Max Act: 6.6497. Min Act: -0.1700
Data Index: 665531 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3060. Min Range: -7.3060
Max Act: 6.6185. Min Act: -0.1700
Data Index: 6209235 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3060. Min Range: -7.3060
Max Act: 6.6185. Min Act: -0.1700
Data Index: 4612423 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19