Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3265 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.2894. Min Act: -0.1700
Data Index: 5791277 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.1019. Min Act: -0.1700
Data Index: 3292517 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.0394. Min Act: -0.1700
Data Index: 6372277 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.0081. Min Act: -0.1700
Data Index: 2270632 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.9769. Min Act: -0.1700
Data Index: 4737350 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.9144. Min Act: -0.1700
Data Index: 8118824 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.9144. Min Act: -0.1700
Data Index: 8679267 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.8831. Min Act: -0.1700
Data Index: 4444755 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.8519. Min Act: -0.1700
Data Index: 8830200 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.8519. Min Act: -0.1700
Data Index: 1551809 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.8519. Min Act: -0.1700
Data Index: 6972366 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.8519. Min Act: -0.1700
Data Index: 8016810 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.8206. Min Act: -0.1700
Data Index: 2159148 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.7894. Min Act: -0.1700
Data Index: 4320388 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.7894. Min Act: -0.1700
Data Index: 6314587 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.7269. Min Act: -0.1700
Data Index: 2917311 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.7581. Min Act: -0.1700
Data Index: 4203458 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.7269. Min Act: -0.1700
Data Index: 3482196 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.7269. Min Act: -0.1700
Data Index: 1112572 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.6956. Min Act: -0.1700
Data Index: 4618238 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #19