Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1928 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1083. Min Range: -7.1083
Max Act: 7.1083. Min Act: -0.1700
Data Index: 6336107 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1083. Min Range: -7.1083
Max Act: 6.9520. Min Act: -0.1700
Data Index: 918409 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1083. Min Range: -7.1083
Max Act: 6.9520. Min Act: -0.1700
Data Index: 7159903 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1083. Min Range: -7.1083
Max Act: 6.7333. Min Act: -0.1700
Data Index: 8801599 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1083. Min Range: -7.1083
Max Act: 6.7333. Min Act: -0.1700
Data Index: 495949 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1083. Min Range: -7.1083
Max Act: 6.7020. Min Act: -0.1700
Data Index: 6703297 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1083. Min Range: -7.1083
Max Act: 6.6395. Min Act: -0.1700
Data Index: 3216048 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1083. Min Range: -7.1083
Max Act: 6.6395. Min Act: -0.1700
Data Index: 5633981 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1083. Min Range: -7.1083
Max Act: 6.6083. Min Act: -0.1700
Data Index: 5986713 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1083. Min Range: -7.1083
Max Act: 6.5770. Min Act: -0.1700
Data Index: 2984543 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1083. Min Range: -7.1083
Max Act: 6.5458. Min Act: -0.1700
Data Index: 3265364 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1083. Min Range: -7.1083
Max Act: 6.5770. Min Act: -0.1700
Data Index: 6607131 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1083. Min Range: -7.1083
Max Act: 6.5145. Min Act: -0.1700
Data Index: 4200362 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1083. Min Range: -7.1083
Max Act: 6.5145. Min Act: -0.1700
Data Index: 4771434 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1083. Min Range: -7.1083
Max Act: 6.4833. Min Act: -0.1700
Data Index: 1625298 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1083. Min Range: -7.1083
Max Act: 6.4520. Min Act: -0.1700
Data Index: 7512679 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1083. Min Range: -7.1083
Max Act: 6.4833. Min Act: -0.1700
Data Index: 3173784 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1083. Min Range: -7.1083
Max Act: 6.4833. Min Act: -0.1700
Data Index: 823222 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1083. Min Range: -7.1083
Max Act: 6.4520. Min Act: -0.1700
Data Index: 8427993 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1083. Min Range: -7.1083
Max Act: 6.4520. Min Act: -0.1700
Data Index: 7998173 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19