Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4028 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8143. Min Range: -7.8143
Max Act: 7.8143. Min Act: -0.1700
Data Index: 3924979 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8143. Min Range: -7.8143
Max Act: 7.6893. Min Act: -0.1700
Data Index: 2778552 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8143. Min Range: -7.8143
Max Act: 7.5331. Min Act: -0.1700
Data Index: 6822813 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8143. Min Range: -7.8143
Max Act: 7.5018. Min Act: -0.1700
Data Index: 6050892 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8143. Min Range: -7.8143
Max Act: 7.4393. Min Act: -0.1700
Data Index: 1907880 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8143. Min Range: -7.8143
Max Act: 7.4706. Min Act: -0.1700
Data Index: 1055097 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8143. Min Range: -7.8143
Max Act: 7.4081. Min Act: -0.1700
Data Index: 2258624 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8143. Min Range: -7.8143
Max Act: 7.3768. Min Act: -0.1700
Data Index: 4937887 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8143. Min Range: -7.8143
Max Act: 7.3456. Min Act: -0.1700
Data Index: 5432669 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8143. Min Range: -7.8143
Max Act: 7.2831. Min Act: -0.1700
Data Index: 3261512 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8143. Min Range: -7.8143
Max Act: 7.3143. Min Act: -0.1700
Data Index: 7681804 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8143. Min Range: -7.8143
Max Act: 7.2206. Min Act: -0.1700
Data Index: 4161319 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8143. Min Range: -7.8143
Max Act: 7.2206. Min Act: -0.1700
Data Index: 4927798 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8143. Min Range: -7.8143
Max Act: 7.1893. Min Act: -0.1700
Data Index: 6037653 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8143. Min Range: -7.8143
Max Act: 7.1893. Min Act: -0.1700
Data Index: 2607209 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8143. Min Range: -7.8143
Max Act: 7.1893. Min Act: -0.1700
Data Index: 1998841 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8143. Min Range: -7.8143
Max Act: 7.2206. Min Act: -0.1700
Data Index: 8598705 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8143. Min Range: -7.8143
Max Act: 7.1581. Min Act: -0.1700
Data Index: 4161866 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8143. Min Range: -7.8143
Max Act: 7.1268. Min Act: -0.1700
Data Index: 3505304 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8143. Min Range: -7.8143
Max Act: 7.1268. Min Act: -0.1700
Data Index: 2590003 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #19