Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2093 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5268. Min Range: -8.5268
Max Act: 8.5268. Min Act: -0.1700
Data Index: 3991005 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5268. Min Range: -8.5268
Max Act: 8.4018. Min Act: -0.1700
Data Index: 3990998 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5268. Min Range: -8.5268
Max Act: 8.2768. Min Act: -0.1700
Data Index: 8481666 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5268. Min Range: -8.5268
Max Act: 8.2143. Min Act: -0.1700
Data Index: 6251363 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5268. Min Range: -8.5268
Max Act: 8.1518. Min Act: -0.1700
Data Index: 7851983 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5268. Min Range: -8.5268
Max Act: 8.0893. Min Act: -0.1700
Data Index: 1818209 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5268. Min Range: -8.5268
Max Act: 8.0893. Min Act: -0.1700
Data Index: 5773264 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5268. Min Range: -8.5268
Max Act: 8.0893. Min Act: -0.1700
Data Index: 7851994 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5268. Min Range: -8.5268
Max Act: 8.0268. Min Act: -0.1700
Data Index: 4582084 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5268. Min Range: -8.5268
Max Act: 8.0268. Min Act: -0.1700
Data Index: 6346804 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5268. Min Range: -8.5268
Max Act: 7.9643. Min Act: -0.1700
Data Index: 285343 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5268. Min Range: -8.5268
Max Act: 7.9643. Min Act: -0.1700
Data Index: 6078576 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5268. Min Range: -8.5268
Max Act: 7.9643. Min Act: -0.1700
Data Index: 7625637 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5268. Min Range: -8.5268
Max Act: 7.9018. Min Act: -0.1700
Data Index: 4667290 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5268. Min Range: -8.5268
Max Act: 7.8393. Min Act: -0.1700
Data Index: 1001059 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5268. Min Range: -8.5268
Max Act: 7.8393. Min Act: -0.1700
Data Index: 1822417 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5268. Min Range: -8.5268
Max Act: 7.8393. Min Act: -0.1700
Data Index: 7724575 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5268. Min Range: -8.5268
Max Act: 7.7143. Min Act: -0.1700
Data Index: 5709602 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5268. Min Range: -8.5268
Max Act: 7.7768. Min Act: -0.1700
Data Index: 5387125 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5268. Min Range: -8.5268
Max Act: 7.7768. Min Act: -0.1700
Data Index: 2968650 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19