Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2793 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2257. Min Range: -3.2257
Max Act: 3.2100. Min Act: -0.1700
Data Index: 2760356 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2257. Min Range: -3.2257
Max Act: 3.2257. Min Act: -0.1700
Data Index: 7905178 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2257. Min Range: -3.2257
Max Act: 3.0840. Min Act: -0.1700
Data Index: 1687247 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2257. Min Range: -3.2257
Max Act: 3.0525. Min Act: -0.1700
Data Index: 3450456 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2257. Min Range: -3.2257
Max Act: 3.0683. Min Act: -0.1700
Data Index: 2032319 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2257. Min Range: -3.2257
Max Act: 3.0367. Min Act: -0.1700
Data Index: 3842880 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2257. Min Range: -3.2257
Max Act: 3.0367. Min Act: -0.1700
Data Index: 5997110 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2257. Min Range: -3.2257
Max Act: 3.0209. Min Act: -0.1700
Data Index: 968149 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2257. Min Range: -3.2257
Max Act: 3.0209. Min Act: -0.1700
Data Index: 3479833 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2257. Min Range: -3.2257
Max Act: 3.0051. Min Act: -0.1700
Data Index: 4973265 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2257. Min Range: -3.2257
Max Act: 3.0051. Min Act: -0.1700
Data Index: 4956144 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2257. Min Range: -3.2257
Max Act: 2.9735. Min Act: -0.1700
Data Index: 3482276 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2257. Min Range: -3.2257
Max Act: 2.9893. Min Act: -0.1700
Data Index: 258332 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2257. Min Range: -3.2257
Max Act: 2.9893. Min Act: -0.1700
Data Index: 6282027 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2257. Min Range: -3.2257
Max Act: 2.9893. Min Act: -0.1700
Data Index: 6141776 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2257. Min Range: -3.2257
Max Act: 3.0051. Min Act: -0.1700
Data Index: 8534425 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2257. Min Range: -3.2257
Max Act: 2.9577. Min Act: -0.1700
Data Index: 1612979 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2257. Min Range: -3.2257
Max Act: 2.9735. Min Act: -0.1700
Data Index: 4047663 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2257. Min Range: -3.2257
Max Act: 2.9735. Min Act: -0.1700
Data Index: 7120398 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2257. Min Range: -3.2257
Max Act: 2.9893. Min Act: -0.1700
Data Index: 7773756 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19