Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 927 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9924. Min Range: -5.9924
Max Act: 5.9924. Min Act: -0.1700
Data Index: 743847 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9924. Min Range: -5.9924
Max Act: 5.8987. Min Act: -0.1700
Data Index: 3586592 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9924. Min Range: -5.9924
Max Act: 5.8049. Min Act: -0.1700
Data Index: 6913560 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9924. Min Range: -5.9924
Max Act: 5.7737. Min Act: -0.1700
Data Index: 6152599 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9924. Min Range: -5.9924
Max Act: 5.7424. Min Act: -0.1700
Data Index: 8643227 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9924. Min Range: -5.9924
Max Act: 5.7424. Min Act: -0.1700
Data Index: 661700 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9924. Min Range: -5.9924
Max Act: 5.7424. Min Act: -0.1700
Data Index: 1722199 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9924. Min Range: -5.9924
Max Act: 5.7737. Min Act: -0.1700
Data Index: 4059243 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9924. Min Range: -5.9924
Max Act: 5.7112. Min Act: -0.1700
Data Index: 141437 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9924. Min Range: -5.9924
Max Act: 5.6799. Min Act: -0.1700
Data Index: 3045998 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9924. Min Range: -5.9924
Max Act: 5.6174. Min Act: -0.1700
Data Index: 6091293 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9924. Min Range: -5.9924
Max Act: 5.5862. Min Act: -0.1700
Data Index: 1038660 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9924. Min Range: -5.9924
Max Act: 5.5862. Min Act: -0.1700
Data Index: 3906809 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9924. Min Range: -5.9924
Max Act: 5.5862. Min Act: -0.1700
Data Index: 5385242 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9924. Min Range: -5.9924
Max Act: 5.5862. Min Act: -0.1700
Data Index: 8120049 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9924. Min Range: -5.9924
Max Act: 5.5862. Min Act: -0.1700
Data Index: 4692331 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9924. Min Range: -5.9924
Max Act: 5.6174. Min Act: -0.1700
Data Index: 2959558 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9924. Min Range: -5.9924
Max Act: 5.5549. Min Act: -0.1700
Data Index: 636242 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9924. Min Range: -5.9924
Max Act: 5.5549. Min Act: -0.1700
Data Index: 1740754 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9924. Min Range: -5.9924
Max Act: 5.5237. Min Act: -0.1700
Data Index: 5612416 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19