Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5378 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5176. Min Range: -2.5176
Max Act: 2.5176. Min Act: -0.1700
Data Index: 906079 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5176. Min Range: -2.5176
Max Act: 2.3876. Min Act: -0.1700
Data Index: 102106 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5176. Min Range: -2.5176
Max Act: 2.3385. Min Act: -0.1700
Data Index: 589082 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5176. Min Range: -2.5176
Max Act: 2.3220. Min Act: -0.1700
Data Index: 3127303 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5176. Min Range: -2.5176
Max Act: 2.3220. Min Act: -0.1700
Data Index: 8490901 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5176. Min Range: -2.5176
Max Act: 2.3056. Min Act: -0.1700
Data Index: 4856436 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5176. Min Range: -2.5176
Max Act: 2.2892. Min Act: -0.1700
Data Index: 2905791 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5176. Min Range: -2.5176
Max Act: 2.3056. Min Act: -0.1700
Data Index: 4317651 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5176. Min Range: -2.5176
Max Act: 2.2892. Min Act: -0.1700
Data Index: 8334666 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5176. Min Range: -2.5176
Max Act: 2.2727. Min Act: -0.1700
Data Index: 7467507 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5176. Min Range: -2.5176
Max Act: 2.2562. Min Act: -0.1700
Data Index: 102105 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5176. Min Range: -2.5176
Max Act: 2.2562. Min Act: -0.1700
Data Index: 4250600 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5176. Min Range: -2.5176
Max Act: 2.2562. Min Act: -0.1700
Data Index: 8709765 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5176. Min Range: -2.5176
Max Act: 2.2562. Min Act: -0.1700
Data Index: 1744800 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5176. Min Range: -2.5176
Max Act: 2.2562. Min Act: -0.1700
Data Index: 1662417 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5176. Min Range: -2.5176
Max Act: 2.2396. Min Act: -0.1700
Data Index: 2898119 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5176. Min Range: -2.5176
Max Act: 2.2562. Min Act: -0.1700
Data Index: 5967395 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5176. Min Range: -2.5176
Max Act: 2.2396. Min Act: -0.1700
Data Index: 6804381 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5176. Min Range: -2.5176
Max Act: 2.2396. Min Act: -0.1700
Data Index: 1323194 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5176. Min Range: -2.5176
Max Act: 2.2396. Min Act: -0.1700
Data Index: 2099278 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19