Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4424 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1196. Min Range: -6.1196
Max Act: 6.1196. Min Act: -0.1700
Data Index: 5898398 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1196. Min Range: -6.1196
Max Act: 6.1196. Min Act: -0.1700
Data Index: 5238635 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1196. Min Range: -6.1196
Max Act: 5.9633. Min Act: -0.1700
Data Index: 4403786 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1196. Min Range: -6.1196
Max Act: 5.9321. Min Act: -0.1700
Data Index: 3678589 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1196. Min Range: -6.1196
Max Act: 5.9321. Min Act: -0.1700
Data Index: 8581549 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1196. Min Range: -6.1196
Max Act: 5.9321. Min Act: -0.1700
Data Index: 3099806 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1196. Min Range: -6.1196
Max Act: 5.9008. Min Act: -0.1700
Data Index: 279251 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1196. Min Range: -6.1196
Max Act: 5.9321. Min Act: -0.1700
Data Index: 5676167 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1196. Min Range: -6.1196
Max Act: 5.9008. Min Act: -0.1700
Data Index: 2372283 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1196. Min Range: -6.1196
Max Act: 5.8383. Min Act: -0.1700
Data Index: 6585570 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1196. Min Range: -6.1196
Max Act: 5.8696. Min Act: -0.1700
Data Index: 3506148 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1196. Min Range: -6.1196
Max Act: 5.8383. Min Act: -0.1700
Data Index: 6983918 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1196. Min Range: -6.1196
Max Act: 5.8383. Min Act: -0.1700
Data Index: 8434689 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1196. Min Range: -6.1196
Max Act: 5.8071. Min Act: -0.1700
Data Index: 5375143 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1196. Min Range: -6.1196
Max Act: 5.8071. Min Act: -0.1700
Data Index: 8449669 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1196. Min Range: -6.1196
Max Act: 5.8071. Min Act: -0.1700
Data Index: 7414364 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1196. Min Range: -6.1196
Max Act: 5.8071. Min Act: -0.1700
Data Index: 655098 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1196. Min Range: -6.1196
Max Act: 5.8071. Min Act: -0.1700
Data Index: 8740031 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1196. Min Range: -6.1196
Max Act: 5.8383. Min Act: -0.1700
Data Index: 5476200 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1196. Min Range: -6.1196
Max Act: 5.7758. Min Act: -0.1700
Data Index: 7243949 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19