Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3531 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4120. Min Range: -6.4120
Max Act: 6.4120. Min Act: -0.1700
Data Index: 3120267 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4120. Min Range: -6.4120
Max Act: 6.1620. Min Act: -0.1700
Data Index: 1764196 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4120. Min Range: -6.4120
Max Act: 6.1620. Min Act: -0.1700
Data Index: 7161312 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4120. Min Range: -6.4120
Max Act: 6.1307. Min Act: -0.1700
Data Index: 5133095 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4120. Min Range: -6.4120
Max Act: 6.1307. Min Act: -0.1700
Data Index: 1610375 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4120. Min Range: -6.4120
Max Act: 6.1307. Min Act: -0.1700
Data Index: 8362199 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4120. Min Range: -6.4120
Max Act: 6.0995. Min Act: -0.1700
Data Index: 6844433 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4120. Min Range: -6.4120
Max Act: 6.0995. Min Act: -0.1700
Data Index: 5256733 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4120. Min Range: -6.4120
Max Act: 6.0682. Min Act: -0.1700
Data Index: 5387174 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4120. Min Range: -6.4120
Max Act: 6.0995. Min Act: -0.1700
Data Index: 8578312 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4120. Min Range: -6.4120
Max Act: 6.0682. Min Act: -0.1700
Data Index: 7260153 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4120. Min Range: -6.4120
Max Act: 6.0057. Min Act: -0.1700
Data Index: 6476486 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4120. Min Range: -6.4120
Max Act: 6.0370. Min Act: -0.1700
Data Index: 3283104 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4120. Min Range: -6.4120
Max Act: 6.0057. Min Act: -0.1700
Data Index: 311776 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4120. Min Range: -6.4120
Max Act: 6.0057. Min Act: -0.1700
Data Index: 4496922 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4120. Min Range: -6.4120
Max Act: 5.9745. Min Act: -0.1700
Data Index: 3469940 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4120. Min Range: -6.4120
Max Act: 5.9745. Min Act: -0.1700
Data Index: 5723031 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4120. Min Range: -6.4120
Max Act: 5.9432. Min Act: -0.1700
Data Index: 5339832 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4120. Min Range: -6.4120
Max Act: 5.9745. Min Act: -0.1700
Data Index: 1610371 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4120. Min Range: -6.4120
Max Act: 5.9745. Min Act: -0.1700
Data Index: 4966474 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #19