Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3644 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1734. Min Range: -6.1734
Max Act: 6.1734. Min Act: -0.1700
Data Index: 3717504 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1734. Min Range: -6.1734
Max Act: 6.1109. Min Act: -0.1700
Data Index: 5414945 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1734. Min Range: -6.1734
Max Act: 6.0171. Min Act: -0.1700
Data Index: 277584 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1734. Min Range: -6.1734
Max Act: 6.0171. Min Act: -0.1700
Data Index: 7407284 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1734. Min Range: -6.1734
Max Act: 6.0171. Min Act: -0.1700
Data Index: 8117791 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1734. Min Range: -6.1734
Max Act: 5.9859. Min Act: -0.1700
Data Index: 3934148 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1734. Min Range: -6.1734
Max Act: 5.9859. Min Act: -0.1700
Data Index: 5673382 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1734. Min Range: -6.1734
Max Act: 5.9546. Min Act: -0.1700
Data Index: 837840 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1734. Min Range: -6.1734
Max Act: 5.9859. Min Act: -0.1700
Data Index: 679072 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1734. Min Range: -6.1734
Max Act: 5.8921. Min Act: -0.1700
Data Index: 4762691 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1734. Min Range: -6.1734
Max Act: 5.8921. Min Act: -0.1700
Data Index: 1498492 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1734. Min Range: -6.1734
Max Act: 5.7359. Min Act: -0.1700
Data Index: 1519882 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1734. Min Range: -6.1734
Max Act: 5.7359. Min Act: -0.1700
Data Index: 6971740 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1734. Min Range: -6.1734
Max Act: 5.7359. Min Act: -0.1700
Data Index: 2250553 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1734. Min Range: -6.1734
Max Act: 5.7046. Min Act: -0.1700
Data Index: 783046 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1734. Min Range: -6.1734
Max Act: 5.7046. Min Act: -0.1700
Data Index: 7127224 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1734. Min Range: -6.1734
Max Act: 5.6734. Min Act: -0.1700
Data Index: 7046318 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1734. Min Range: -6.1734
Max Act: 5.6734. Min Act: -0.1700
Data Index: 3467073 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1734. Min Range: -6.1734
Max Act: 5.6734. Min Act: -0.1700
Data Index: 5050086 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1734. Min Range: -6.1734
Max Act: 5.6734. Min Act: -0.1700
Data Index: 5874905 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #19