Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2539 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5405. Min Range: -6.5405
Max Act: 6.5405. Min Act: -0.1700
Data Index: 1198215 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5405. Min Range: -6.5405
Max Act: 6.2592. Min Act: -0.1700
Data Index: 1234055 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5405. Min Range: -6.5405
Max Act: 6.1342. Min Act: -0.1700
Data Index: 1568198 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5405. Min Range: -6.5405
Max Act: 6.0092. Min Act: -0.1700
Data Index: 5989915 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5405. Min Range: -6.5405
Max Act: 5.9780. Min Act: -0.1700
Data Index: 5451279 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5405. Min Range: -6.5405
Max Act: 5.9155. Min Act: -0.1700
Data Index: 4946363 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5405. Min Range: -6.5405
Max Act: 5.8842. Min Act: -0.1700
Data Index: 5752075 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5405. Min Range: -6.5405
Max Act: 5.8530. Min Act: -0.1700
Data Index: 6656132 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5405. Min Range: -6.5405
Max Act: 5.8842. Min Act: -0.1700
Data Index: 853648 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5405. Min Range: -6.5405
Max Act: 5.8842. Min Act: -0.1700
Data Index: 3753921 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5405. Min Range: -6.5405
Max Act: 5.9155. Min Act: -0.1700
Data Index: 8474278 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5405. Min Range: -6.5405
Max Act: 5.8842. Min Act: -0.1700
Data Index: 5226063 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5405. Min Range: -6.5405
Max Act: 5.8530. Min Act: -0.1700
Data Index: 3526253 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5405. Min Range: -6.5405
Max Act: 5.8530. Min Act: -0.1700
Data Index: 6540320 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5405. Min Range: -6.5405
Max Act: 5.8530. Min Act: -0.1700
Data Index: 6545394 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5405. Min Range: -6.5405
Max Act: 5.8530. Min Act: -0.1700
Data Index: 7174367 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5405. Min Range: -6.5405
Max Act: 5.8217. Min Act: -0.1700
Data Index: 6207808 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5405. Min Range: -6.5405
Max Act: 5.8217. Min Act: -0.1700
Data Index: 5738415 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5405. Min Range: -6.5405
Max Act: 5.8217. Min Act: -0.1700
Data Index: 876521 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5405. Min Range: -6.5405
Max Act: 5.8530. Min Act: -0.1700
Data Index: 141093 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #19