Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1804 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4369. Min Range: -6.4369
Max Act: 6.4369. Min Act: -0.1700
Data Index: 3329535 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4369. Min Range: -6.4369
Max Act: 6.2182. Min Act: -0.1700
Data Index: 3640536 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4369. Min Range: -6.4369
Max Act: 6.1244. Min Act: -0.1700
Data Index: 4003642 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4369. Min Range: -6.4369
Max Act: 6.0619. Min Act: -0.1700
Data Index: 976444 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4369. Min Range: -6.4369
Max Act: 6.0307. Min Act: -0.1700
Data Index: 3093001 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4369. Min Range: -6.4369
Max Act: 5.9682. Min Act: -0.1700
Data Index: 3196301 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4369. Min Range: -6.4369
Max Act: 5.9369. Min Act: -0.1700
Data Index: 3960150 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4369. Min Range: -6.4369
Max Act: 5.9057. Min Act: -0.1700
Data Index: 2761183 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4369. Min Range: -6.4369
Max Act: 5.8744. Min Act: -0.1700
Data Index: 1501311 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4369. Min Range: -6.4369
Max Act: 5.8744. Min Act: -0.1700
Data Index: 1214127 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4369. Min Range: -6.4369
Max Act: 5.8744. Min Act: -0.1700
Data Index: 3332688 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4369. Min Range: -6.4369
Max Act: 5.9057. Min Act: -0.1700
Data Index: 119900 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4369. Min Range: -6.4369
Max Act: 5.8432. Min Act: -0.1700
Data Index: 1612467 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4369. Min Range: -6.4369
Max Act: 5.8432. Min Act: -0.1700
Data Index: 5164367 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4369. Min Range: -6.4369
Max Act: 5.8432. Min Act: -0.1700
Data Index: 7093827 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4369. Min Range: -6.4369
Max Act: 5.8119. Min Act: -0.1700
Data Index: 4842351 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4369. Min Range: -6.4369
Max Act: 5.8432. Min Act: -0.1700
Data Index: 7028261 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4369. Min Range: -6.4369
Max Act: 5.8119. Min Act: -0.1700
Data Index: 68701 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4369. Min Range: -6.4369
Max Act: 5.8119. Min Act: -0.1700
Data Index: 2955713 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4369. Min Range: -6.4369
Max Act: 5.8119. Min Act: -0.1700
Data Index: 8684480 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19