Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3779 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0829. Min Range: -3.0829
Max Act: 3.0829. Min Act: -0.1700
Data Index: 7081998 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0829. Min Range: -3.0829
Max Act: 3.0040. Min Act: -0.1700
Data Index: 4972681 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0829. Min Range: -3.0829
Max Act: 2.9882. Min Act: -0.1700
Data Index: 2073547 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0829. Min Range: -3.0829
Max Act: 2.9407. Min Act: -0.1700
Data Index: 247268 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0829. Min Range: -3.0829
Max Act: 2.9090. Min Act: -0.1700
Data Index: 6337419 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0829. Min Range: -3.0829
Max Act: 2.9090. Min Act: -0.1700
Data Index: 8600785 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0829. Min Range: -3.0829
Max Act: 2.9090. Min Act: -0.1700
Data Index: 1029481 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0829. Min Range: -3.0829
Max Act: 2.9249. Min Act: -0.1700
Data Index: 2298106 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0829. Min Range: -3.0829
Max Act: 2.8932. Min Act: -0.1700
Data Index: 3646121 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0829. Min Range: -3.0829
Max Act: 2.8773. Min Act: -0.1700
Data Index: 6790903 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0829. Min Range: -3.0829
Max Act: 2.8773. Min Act: -0.1700
Data Index: 1265541 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0829. Min Range: -3.0829
Max Act: 2.8773. Min Act: -0.1700
Data Index: 4793625 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0829. Min Range: -3.0829
Max Act: 2.8455. Min Act: -0.1700
Data Index: 8394015 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0829. Min Range: -3.0829
Max Act: 2.8455. Min Act: -0.1700
Data Index: 73317 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0829. Min Range: -3.0829
Max Act: 2.8455. Min Act: -0.1700
Data Index: 3323614 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0829. Min Range: -3.0829
Max Act: 2.8455. Min Act: -0.1700
Data Index: 2197687 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0829. Min Range: -3.0829
Max Act: 2.8296. Min Act: -0.1700
Data Index: 2843778 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0829. Min Range: -3.0829
Max Act: 2.8296. Min Act: -0.1700
Data Index: 3323615 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0829. Min Range: -3.0829
Max Act: 2.8137. Min Act: -0.1700
Data Index: 6286247 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0829. Min Range: -3.0829
Max Act: 2.8296. Min Act: -0.1700
Data Index: 8214134 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #19