Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 851 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3813. Min Range: -6.3813
Max Act: 6.3813. Min Act: -0.1700
Data Index: 5796153 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3813. Min Range: -6.3813
Max Act: 6.1313. Min Act: -0.1700
Data Index: 5796154 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3813. Min Range: -6.3813
Max Act: 6.1001. Min Act: -0.1700
Data Index: 186200 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3813. Min Range: -6.3813
Max Act: 5.9751. Min Act: -0.1700
Data Index: 2615948 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3813. Min Range: -6.3813
Max Act: 5.9126. Min Act: -0.1700
Data Index: 508507 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3813. Min Range: -6.3813
Max Act: 5.8813. Min Act: -0.1700
Data Index: 5917849 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3813. Min Range: -6.3813
Max Act: 5.8813. Min Act: -0.1700
Data Index: 8709803 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3813. Min Range: -6.3813
Max Act: 5.8188. Min Act: -0.1700
Data Index: 8282617 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3813. Min Range: -6.3813
Max Act: 5.7563. Min Act: -0.1700
Data Index: 5502114 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3813. Min Range: -6.3813
Max Act: 5.7563. Min Act: -0.1700
Data Index: 6503678 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3813. Min Range: -6.3813
Max Act: 5.7563. Min Act: -0.1700
Data Index: 4650859 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3813. Min Range: -6.3813
Max Act: 5.6938. Min Act: -0.1700
Data Index: 879192 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3813. Min Range: -6.3813
Max Act: 5.6938. Min Act: -0.1700
Data Index: 3083177 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3813. Min Range: -6.3813
Max Act: 5.6313. Min Act: -0.1700
Data Index: 333418 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3813. Min Range: -6.3813
Max Act: 5.6626. Min Act: -0.1700
Data Index: 7955665 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3813. Min Range: -6.3813
Max Act: 5.6626. Min Act: -0.1700
Data Index: 3801791 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3813. Min Range: -6.3813
Max Act: 5.6626. Min Act: -0.1700
Data Index: 3499511 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3813. Min Range: -6.3813
Max Act: 5.6626. Min Act: -0.1700
Data Index: 8212731 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3813. Min Range: -6.3813
Max Act: 5.6938. Min Act: -0.1700
Data Index: 1113221 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3813. Min Range: -6.3813
Max Act: 5.6313. Min Act: -0.1700
Data Index: 5918120 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #19