Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3574 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.8855. Min Act: -0.1700
Data Index: 6951634 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.7917. Min Act: -0.1700
Data Index: 6858009 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.7605. Min Act: -0.1700
Data Index: 1840923 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.7605. Min Act: -0.1700
Data Index: 331655 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.7605. Min Act: -0.1700
Data Index: 1997612 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.7605. Min Act: -0.1700
Data Index: 4673186 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.6980. Min Act: -0.1700
Data Index: 7172345 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.6667. Min Act: -0.1700
Data Index: 4623333 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.6667. Min Act: -0.1700
Data Index: 8679116 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.6355. Min Act: -0.1700
Data Index: 2468272 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.6042. Min Act: -0.1700
Data Index: 1478132 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.5730. Min Act: -0.1700
Data Index: 5221237 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.5730. Min Act: -0.1700
Data Index: 8815956 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.5417. Min Act: -0.1700
Data Index: 7548943 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.5417. Min Act: -0.1700
Data Index: 7564657 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.5105. Min Act: -0.1700
Data Index: 3000912 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.5417. Min Act: -0.1700
Data Index: 6304099 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.5105. Min Act: -0.1700
Data Index: 1548307 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.5105. Min Act: -0.1700
Data Index: 7228204 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.5105. Min Act: -0.1700
Data Index: 3977092 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19