Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 855 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2775. Min Range: -8.2775
Max Act: 8.2775. Min Act: -0.1700
Data Index: 6747625 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2775. Min Range: -8.2775
Max Act: 8.1525. Min Act: -0.1700
Data Index: 7252103 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2775. Min Range: -8.2775
Max Act: 8.1525. Min Act: -0.1700
Data Index: 552007 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2775. Min Range: -8.2775
Max Act: 8.0275. Min Act: -0.1700
Data Index: 2657390 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2775. Min Range: -8.2775
Max Act: 7.9650. Min Act: -0.1700
Data Index: 4309049 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2775. Min Range: -8.2775
Max Act: 7.9650. Min Act: -0.1700
Data Index: 8006773 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2775. Min Range: -8.2775
Max Act: 7.9025. Min Act: -0.1700
Data Index: 5851151 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2775. Min Range: -8.2775
Max Act: 7.9025. Min Act: -0.1700
Data Index: 6508128 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2775. Min Range: -8.2775
Max Act: 7.9650. Min Act: -0.1700
Data Index: 434212 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2775. Min Range: -8.2775
Max Act: 7.9025. Min Act: -0.1700
Data Index: 6372592 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2775. Min Range: -8.2775
Max Act: 7.8400. Min Act: -0.1700
Data Index: 7430563 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2775. Min Range: -8.2775
Max Act: 7.8400. Min Act: -0.1700
Data Index: 7365221 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2775. Min Range: -8.2775
Max Act: 7.7775. Min Act: -0.1700
Data Index: 3454842 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2775. Min Range: -8.2775
Max Act: 7.8400. Min Act: -0.1700
Data Index: 3105207 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2775. Min Range: -8.2775
Max Act: 7.8400. Min Act: -0.1700
Data Index: 1402342 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2775. Min Range: -8.2775
Max Act: 7.7775. Min Act: -0.1700
Data Index: 157305 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2775. Min Range: -8.2775
Max Act: 7.7775. Min Act: -0.1700
Data Index: 4810856 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2775. Min Range: -8.2775
Max Act: 7.7775. Min Act: -0.1700
Data Index: 2725936 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2775. Min Range: -8.2775
Max Act: 7.7775. Min Act: -0.1700
Data Index: 2003763 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2775. Min Range: -8.2775
Max Act: 7.7775. Min Act: -0.1700
Data Index: 8326952 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19