Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1982 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.9072. Min Act: -0.1700
Data Index: 3568866 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.6884. Min Act: -0.1700
Data Index: 7863223 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.5947. Min Act: -0.1700
Data Index: 6420961 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.5634. Min Act: -0.1700
Data Index: 5308713 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.5009. Min Act: -0.1700
Data Index: 2106950 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.5009. Min Act: -0.1700
Data Index: 7569961 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.5009. Min Act: -0.1700
Data Index: 3377446 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.5009. Min Act: -0.1700
Data Index: 3961735 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.4697. Min Act: -0.1700
Data Index: 1370444 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.4697. Min Act: -0.1700
Data Index: 2752906 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.5009. Min Act: -0.1700
Data Index: 730385 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.4384. Min Act: -0.1700
Data Index: 2392837 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.4384. Min Act: -0.1700
Data Index: 7640600 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.4072. Min Act: -0.1700
Data Index: 6818244 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.3759. Min Act: -0.1700
Data Index: 5706985 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.4072. Min Act: -0.1700
Data Index: 7160249 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.3759. Min Act: -0.1700
Data Index: 3641845 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.3759. Min Act: -0.1700
Data Index: 3019354 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.3759. Min Act: -0.1700
Data Index: 2752908 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9072. Min Range: -5.9072
Max Act: 5.3759. Min Act: -0.1700
Data Index: 7867655 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #19