Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3389 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1235. Min Range: -3.1235
Max Act: 3.1235. Min Act: -0.1700
Data Index: 5084003 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1235. Min Range: -3.1235
Max Act: 3.1077. Min Act: -0.1700
Data Index: 6318871 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1235. Min Range: -3.1235
Max Act: 3.0446. Min Act: -0.1700
Data Index: 2685665 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1235. Min Range: -3.1235
Max Act: 3.0288. Min Act: -0.1700
Data Index: 3460460 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1235. Min Range: -3.1235
Max Act: 2.9972. Min Act: -0.1700
Data Index: 1439256 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1235. Min Range: -3.1235
Max Act: 2.9972. Min Act: -0.1700
Data Index: 7916386 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1235. Min Range: -3.1235
Max Act: 2.9972. Min Act: -0.1700
Data Index: 8817728 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1235. Min Range: -3.1235
Max Act: 2.9972. Min Act: -0.1700
Data Index: 1481121 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1235. Min Range: -3.1235
Max Act: 2.9972. Min Act: -0.1700
Data Index: 3460462 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1235. Min Range: -3.1235
Max Act: 2.9814. Min Act: -0.1700
Data Index: 6212039 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1235. Min Range: -3.1235
Max Act: 2.9814. Min Act: -0.1700
Data Index: 1512246 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1235. Min Range: -3.1235
Max Act: 2.9814. Min Act: -0.1700
Data Index: 6052241 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1235. Min Range: -3.1235
Max Act: 2.9814. Min Act: -0.1700
Data Index: 2605055 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1235. Min Range: -3.1235
Max Act: 2.9498. Min Act: -0.1700
Data Index: 2949078 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1235. Min Range: -3.1235
Max Act: 2.9656. Min Act: -0.1700
Data Index: 3917068 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1235. Min Range: -3.1235
Max Act: 2.9498. Min Act: -0.1700
Data Index: 6212038 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1235. Min Range: -3.1235
Max Act: 2.9340. Min Act: -0.1700
Data Index: 4317896 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1235. Min Range: -3.1235
Max Act: 2.9340. Min Act: -0.1700
Data Index: 5981105 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1235. Min Range: -3.1235
Max Act: 2.9340. Min Act: -0.1700
Data Index: 3889030 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1235. Min Range: -3.1235
Max Act: 2.9181. Min Act: -0.1700
Data Index: 44012 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #19