Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2795 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.5187. Min Act: -0.1700
Data Index: 8345206 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.2687. Min Act: -0.1700
Data Index: 3215076 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.2062. Min Act: -0.1700
Data Index: 8649189 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.1437. Min Act: -0.1700
Data Index: 90337 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.1437. Min Act: -0.1700
Data Index: 912206 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.1124. Min Act: -0.1700
Data Index: 706592 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.1124. Min Act: -0.1700
Data Index: 5232349 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.0812. Min Act: -0.1700
Data Index: 5059325 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.0812. Min Act: -0.1700
Data Index: 5651887 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.0812. Min Act: -0.1700
Data Index: 3318271 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.0499. Min Act: -0.1700
Data Index: 1019816 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.0187. Min Act: -0.1700
Data Index: 5321500 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.0187. Min Act: -0.1700
Data Index: 3761634 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5187. Min Range: -5.5187
Max Act: 4.9874. Min Act: -0.1700
Data Index: 6739214 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.0187. Min Act: -0.1700
Data Index: 4915010 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.0187. Min Act: -0.1700
Data Index: 6156835 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5187. Min Range: -5.5187
Max Act: 4.9874. Min Act: -0.1700
Data Index: 7114945 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.0187. Min Act: -0.1700
Data Index: 1195577 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5187. Min Range: -5.5187
Max Act: 4.9874. Min Act: -0.1700
Data Index: 2408953 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5187. Min Range: -5.5187
Max Act: 4.9874. Min Act: -0.1700
Data Index: 4796340 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #19