Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3266 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0379. Min Range: -6.0379
Max Act: 6.0379. Min Act: -0.1700
Data Index: 2314502 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0379. Min Range: -6.0379
Max Act: 6.0379. Min Act: -0.1700
Data Index: 4634701 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0379. Min Range: -6.0379
Max Act: 5.8817. Min Act: -0.1700
Data Index: 4618016 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0379. Min Range: -6.0379
Max Act: 5.8504. Min Act: -0.1700
Data Index: 4314070 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0379. Min Range: -6.0379
Max Act: 5.8192. Min Act: -0.1700
Data Index: 952827 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0379. Min Range: -6.0379
Max Act: 5.7879. Min Act: -0.1700
Data Index: 2927874 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0379. Min Range: -6.0379
Max Act: 5.7879. Min Act: -0.1700
Data Index: 3196786 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0379. Min Range: -6.0379
Max Act: 5.7567. Min Act: -0.1700
Data Index: 27045 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0379. Min Range: -6.0379
Max Act: 5.7254. Min Act: -0.1700
Data Index: 4827050 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0379. Min Range: -6.0379
Max Act: 5.7254. Min Act: -0.1700
Data Index: 2750444 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0379. Min Range: -6.0379
Max Act: 5.6942. Min Act: -0.1700
Data Index: 2969487 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0379. Min Range: -6.0379
Max Act: 5.6629. Min Act: -0.1700
Data Index: 5587576 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0379. Min Range: -6.0379
Max Act: 5.6629. Min Act: -0.1700
Data Index: 7632253 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0379. Min Range: -6.0379
Max Act: 5.6317. Min Act: -0.1700
Data Index: 7058794 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0379. Min Range: -6.0379
Max Act: 5.6004. Min Act: -0.1700
Data Index: 280189 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0379. Min Range: -6.0379
Max Act: 5.5379. Min Act: -0.1700
Data Index: 3557644 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0379. Min Range: -6.0379
Max Act: 5.5692. Min Act: -0.1700
Data Index: 8339963 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0379. Min Range: -6.0379
Max Act: 5.5692. Min Act: -0.1700
Data Index: 8525720 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0379. Min Range: -6.0379
Max Act: 5.5692. Min Act: -0.1700
Data Index: 6579212 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0379. Min Range: -6.0379
Max Act: 5.5379. Min Act: -0.1700
Data Index: 13904 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #19