Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2562 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8279. Min Range: -10.8279
Max Act: 10.8279. Min Act: -0.1700
Data Index: 4417092 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8279. Min Range: -10.8279
Max Act: 10.7029. Min Act: -0.1700
Data Index: 3324044 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8279. Min Range: -10.8279
Max Act: 10.5779. Min Act: -0.1700
Data Index: 1188687 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8279. Min Range: -10.8279
Max Act: 10.4529. Min Act: -0.1700
Data Index: 1736635 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8279. Min Range: -10.8279
Max Act: 10.2654. Min Act: -0.1700
Data Index: 5144350 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8279. Min Range: -10.8279
Max Act: 10.2029. Min Act: -0.1700
Data Index: 8000774 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8279. Min Range: -10.8279
Max Act: 10.2029. Min Act: -0.1700
Data Index: 8334907 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8279. Min Range: -10.8279
Max Act: 10.1404. Min Act: -0.1700
Data Index: 1075882 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8279. Min Range: -10.8279
Max Act: 10.0154. Min Act: -0.1700
Data Index: 2113757 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8279. Min Range: -10.8279
Max Act: 9.9529. Min Act: -0.1698
Data Index: 2374039 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8279. Min Range: -10.8279
Max Act: 9.8904. Min Act: -0.1700
Data Index: 5044851 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8279. Min Range: -10.8279
Max Act: 9.8904. Min Act: -0.1700
Data Index: 2357443 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8279. Min Range: -10.8279
Max Act: 9.8279. Min Act: -0.1700
Data Index: 3608414 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8279. Min Range: -10.8279
Max Act: 9.8279. Min Act: -0.1700
Data Index: 6773562 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8279. Min Range: -10.8279
Max Act: 9.8279. Min Act: -0.1700
Data Index: 7287416 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8279. Min Range: -10.8279
Max Act: 9.8279. Min Act: -0.1700
Data Index: 2910444 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8279. Min Range: -10.8279
Max Act: 9.8279. Min Act: -0.1700
Data Index: 2337823 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8279. Min Range: -10.8279
Max Act: 9.8279. Min Act: -0.1700
Data Index: 3464133 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8279. Min Range: -10.8279
Max Act: 9.8279. Min Act: -0.1700
Data Index: 2657791 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8279. Min Range: -10.8279
Max Act: 9.8279. Min Act: -0.1700
Data Index: 2991237 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19