Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4786 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.7183. Min Act: -0.1700
Data Index: 3046954 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.6870. Min Act: -0.1700
Data Index: 3402609 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.6870. Min Act: -0.1700
Data Index: 8554207 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.6870. Min Act: -0.1700
Data Index: 2261327 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.6870. Min Act: -0.1700
Data Index: 4300005 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.6870. Min Act: -0.1700
Data Index: 8091275 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.6870. Min Act: -0.1700
Data Index: 8035347 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.6245. Min Act: -0.1700
Data Index: 350632 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.6558. Min Act: -0.1700
Data Index: 2114735 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.6558. Min Act: -0.1700
Data Index: 7718147 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.6558. Min Act: -0.1700
Data Index: 6329434 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.6558. Min Act: -0.1700
Data Index: 6084771 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.6558. Min Act: -0.1700
Data Index: 5981462 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.6558. Min Act: -0.1700
Data Index: 588212 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.6558. Min Act: -0.1700
Data Index: 5037622 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.6558. Min Act: -0.1700
Data Index: 3667573 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.6558. Min Act: -0.1700
Data Index: 3467568 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.6245. Min Act: -0.1700
Data Index: 1054727 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.5932. Min Act: -0.1700
Data Index: 2710843 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7183. Min Range: -3.7183
Max Act: 3.6245. Min Act: -0.1700
Data Index: 2890537 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19