Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 17 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0186. Min Range: -4.0186
Max Act: 3.9873. Min Act: -0.1700
Data Index: 1162463 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0186. Min Range: -4.0186
Max Act: 3.9560. Min Act: -0.1700
Data Index: 3943952 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0186. Min Range: -4.0186
Max Act: 4.0186. Min Act: -0.1700
Data Index: 7728367 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0186. Min Range: -4.0186
Max Act: 3.9248. Min Act: -0.1700
Data Index: 4077031 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0186. Min Range: -4.0186
Max Act: 3.9248. Min Act: -0.1700
Data Index: 2341896 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0186. Min Range: -4.0186
Max Act: 3.9560. Min Act: -0.1700
Data Index: 2217194 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0186. Min Range: -4.0186
Max Act: 3.9248. Min Act: -0.1700
Data Index: 5126303 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0186. Min Range: -4.0186
Max Act: 3.9248. Min Act: -0.1700
Data Index: 4376751 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0186. Min Range: -4.0186
Max Act: 3.9248. Min Act: -0.1700
Data Index: 4256462 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0186. Min Range: -4.0186
Max Act: 3.9248. Min Act: -0.1700
Data Index: 8762696 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0186. Min Range: -4.0186
Max Act: 3.8935. Min Act: -0.1700
Data Index: 3190129 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0186. Min Range: -4.0186
Max Act: 3.8622. Min Act: -0.1700
Data Index: 6429889 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0186. Min Range: -4.0186
Max Act: 3.8935. Min Act: -0.1700
Data Index: 7054515 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0186. Min Range: -4.0186
Max Act: 3.8935. Min Act: -0.1700
Data Index: 4118421 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0186. Min Range: -4.0186
Max Act: 3.8622. Min Act: -0.1700
Data Index: 7336384 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0186. Min Range: -4.0186
Max Act: 3.8935. Min Act: -0.1700
Data Index: 6103940 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0186. Min Range: -4.0186
Max Act: 3.8935. Min Act: -0.1700
Data Index: 7022829 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0186. Min Range: -4.0186
Max Act: 3.8622. Min Act: -0.1700
Data Index: 4757218 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0186. Min Range: -4.0186
Max Act: 3.8310. Min Act: -0.1700
Data Index: 1302932 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0186. Min Range: -4.0186
Max Act: 3.7997. Min Act: -0.1700
Data Index: 6213239 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19