Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1833 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3516. Min Range: -9.3516
Max Act: 9.3516. Min Act: -0.1700
Data Index: 3699322 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3516. Min Range: -9.3516
Max Act: 9.2891. Min Act: -0.1700
Data Index: 8083841 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3516. Min Range: -9.3516
Max Act: 9.1016. Min Act: -0.1700
Data Index: 8717809 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3516. Min Range: -9.3516
Max Act: 8.9141. Min Act: -0.1700
Data Index: 6694517 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3516. Min Range: -9.3516
Max Act: 8.9141. Min Act: -0.1700
Data Index: 7059499 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3516. Min Range: -9.3516
Max Act: 8.8516. Min Act: -0.1700
Data Index: 1129093 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3516. Min Range: -9.3516
Max Act: 8.7891. Min Act: -0.1700
Data Index: 7372838 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3516. Min Range: -9.3516
Max Act: 8.6641. Min Act: -0.1700
Data Index: 8315332 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3516. Min Range: -9.3516
Max Act: 8.6641. Min Act: -0.1700
Data Index: 5111682 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3516. Min Range: -9.3516
Max Act: 8.6016. Min Act: -0.1700
Data Index: 4030656 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3516. Min Range: -9.3516
Max Act: 8.6641. Min Act: -0.1700
Data Index: 2682289 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3516. Min Range: -9.3516
Max Act: 8.6016. Min Act: -0.1700
Data Index: 6005827 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3516. Min Range: -9.3516
Max Act: 8.6016. Min Act: -0.1700
Data Index: 6968293 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3516. Min Range: -9.3516
Max Act: 8.6016. Min Act: -0.1700
Data Index: 1566599 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3516. Min Range: -9.3516
Max Act: 8.6016. Min Act: -0.1700
Data Index: 2640321 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3516. Min Range: -9.3516
Max Act: 8.5391. Min Act: -0.1700
Data Index: 5152225 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3516. Min Range: -9.3516
Max Act: 8.5078. Min Act: -0.1700
Data Index: 625550 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3516. Min Range: -9.3516
Max Act: 8.5391. Min Act: -0.1700
Data Index: 1362489 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3516. Min Range: -9.3516
Max Act: 8.5078. Min Act: -0.1700
Data Index: 5626580 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3516. Min Range: -9.3516
Max Act: 8.5078. Min Act: -0.1700
Data Index: 4780550 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #19