Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3383 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3154. Min Range: -6.3154
Max Act: 6.3154. Min Act: -0.1700
Data Index: 3341430 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3154. Min Range: -6.3154
Max Act: 6.3154. Min Act: -0.1700
Data Index: 548859 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3154. Min Range: -6.3154
Max Act: 6.2841. Min Act: -0.1700
Data Index: 7146944 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3154. Min Range: -6.3154
Max Act: 6.2529. Min Act: -0.1700
Data Index: 5016012 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3154. Min Range: -6.3154
Max Act: 6.1904. Min Act: -0.1700
Data Index: 7874949 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3154. Min Range: -6.3154
Max Act: 6.2216. Min Act: -0.1700
Data Index: 4645218 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3154. Min Range: -6.3154
Max Act: 6.1591. Min Act: -0.1700
Data Index: 370675 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3154. Min Range: -6.3154
Max Act: 6.1591. Min Act: -0.1700
Data Index: 3758785 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3154. Min Range: -6.3154
Max Act: 6.1279. Min Act: -0.1700
Data Index: 5665261 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3154. Min Range: -6.3154
Max Act: 6.0654. Min Act: -0.1700
Data Index: 3916796 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3154. Min Range: -6.3154
Max Act: 6.0341. Min Act: -0.1700
Data Index: 3292157 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3154. Min Range: -6.3154
Max Act: 5.9404. Min Act: -0.1700
Data Index: 6350534 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3154. Min Range: -6.3154
Max Act: 5.9716. Min Act: -0.1700
Data Index: 7950473 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3154. Min Range: -6.3154
Max Act: 5.9716. Min Act: -0.1700
Data Index: 5745911 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3154. Min Range: -6.3154
Max Act: 6.0029. Min Act: -0.1700
Data Index: 1727607 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3154. Min Range: -6.3154
Max Act: 5.9404. Min Act: -0.1700
Data Index: 3565450 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3154. Min Range: -6.3154
Max Act: 5.9404. Min Act: -0.1700
Data Index: 8245457 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3154. Min Range: -6.3154
Max Act: 5.9091. Min Act: -0.1700
Data Index: 3000980 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3154. Min Range: -6.3154
Max Act: 5.9404. Min Act: -0.1700
Data Index: 3303422 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3154. Min Range: -6.3154
Max Act: 5.9091. Min Act: -0.1700
Data Index: 2377918 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #19