Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1673 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2001. Min Range: -7.2001
Max Act: 7.2001. Min Act: -0.1700
Data Index: 7762064 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2001. Min Range: -7.2001
Max Act: 6.9501. Min Act: -0.1700
Data Index: 1402817 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2001. Min Range: -7.2001
Max Act: 6.9189. Min Act: -0.1700
Data Index: 3996980 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2001. Min Range: -7.2001
Max Act: 6.9189. Min Act: -0.1700
Data Index: 2811917 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2001. Min Range: -7.2001
Max Act: 6.8564. Min Act: -0.1700
Data Index: 3541846 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2001. Min Range: -7.2001
Max Act: 6.8251. Min Act: -0.1700
Data Index: 6836555 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2001. Min Range: -7.2001
Max Act: 6.7939. Min Act: -0.1700
Data Index: 6666381 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2001. Min Range: -7.2001
Max Act: 6.7939. Min Act: -0.1700
Data Index: 6665465 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2001. Min Range: -7.2001
Max Act: 6.7626. Min Act: -0.1700
Data Index: 8177009 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2001. Min Range: -7.2001
Max Act: 6.7626. Min Act: -0.1700
Data Index: 2989544 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2001. Min Range: -7.2001
Max Act: 6.7314. Min Act: -0.1700
Data Index: 6206499 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2001. Min Range: -7.2001
Max Act: 6.7314. Min Act: -0.1700
Data Index: 7103818 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2001. Min Range: -7.2001
Max Act: 6.7314. Min Act: -0.1700
Data Index: 2919164 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2001. Min Range: -7.2001
Max Act: 6.7314. Min Act: -0.1700
Data Index: 5380269 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2001. Min Range: -7.2001
Max Act: 6.7314. Min Act: -0.1700
Data Index: 8091242 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2001. Min Range: -7.2001
Max Act: 6.6689. Min Act: -0.1700
Data Index: 2183352 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2001. Min Range: -7.2001
Max Act: 6.7001. Min Act: -0.1700
Data Index: 7730246 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2001. Min Range: -7.2001
Max Act: 6.7314. Min Act: -0.1700
Data Index: 4143165 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2001. Min Range: -7.2001
Max Act: 6.6376. Min Act: -0.1700
Data Index: 1230111 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2001. Min Range: -7.2001
Max Act: 6.6689. Min Act: -0.1700
Data Index: 3216204 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19