Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3390 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7504. Min Range: -5.7504
Max Act: 5.7504. Min Act: -0.1700
Data Index: 7680935 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7504. Min Range: -5.7504
Max Act: 5.6879. Min Act: -0.1700
Data Index: 1912212 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7504. Min Range: -5.7504
Max Act: 5.5941. Min Act: -0.1700
Data Index: 2450554 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7504. Min Range: -5.7504
Max Act: 5.5941. Min Act: -0.1700
Data Index: 195065 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7504. Min Range: -5.7504
Max Act: 5.5629. Min Act: -0.1700
Data Index: 6767083 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7504. Min Range: -5.7504
Max Act: 5.5316. Min Act: -0.1700
Data Index: 6228866 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7504. Min Range: -5.7504
Max Act: 5.5004. Min Act: -0.1700
Data Index: 4174831 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7504. Min Range: -5.7504
Max Act: 5.4691. Min Act: -0.1700
Data Index: 7211085 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7504. Min Range: -5.7504
Max Act: 5.5004. Min Act: -0.1700
Data Index: 7351889 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7504. Min Range: -5.7504
Max Act: 5.5004. Min Act: -0.1700
Data Index: 8769979 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7504. Min Range: -5.7504
Max Act: 5.5004. Min Act: -0.1700
Data Index: 8278829 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7504. Min Range: -5.7504
Max Act: 5.5004. Min Act: -0.1700
Data Index: 6616036 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7504. Min Range: -5.7504
Max Act: 5.4379. Min Act: -0.1700
Data Index: 7040898 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7504. Min Range: -5.7504
Max Act: 5.4691. Min Act: -0.1700
Data Index: 6875256 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7504. Min Range: -5.7504
Max Act: 5.4691. Min Act: -0.1700
Data Index: 824300 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7504. Min Range: -5.7504
Max Act: 5.4379. Min Act: -0.1700
Data Index: 2102835 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7504. Min Range: -5.7504
Max Act: 5.4379. Min Act: -0.1700
Data Index: 8251907 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7504. Min Range: -5.7504
Max Act: 5.4379. Min Act: -0.1700
Data Index: 2208019 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7504. Min Range: -5.7504
Max Act: 5.4379. Min Act: -0.1700
Data Index: 2035156 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7504. Min Range: -5.7504
Max Act: 5.4379. Min Act: -0.1700
Data Index: 188621 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19