Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1049 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7004. Min Range: -1.7004
Max Act: 1.7004. Min Act: -0.1700
Data Index: 7269715 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7004. Min Range: -1.7004
Max Act: 1.7004. Min Act: -0.1700
Data Index: 1526169 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7004. Min Range: -1.7004
Max Act: 1.6134. Min Act: -0.1700
Data Index: 3514333 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7004. Min Range: -1.7004
Max Act: 1.6134. Min Act: -0.1700
Data Index: 7581066 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7004. Min Range: -1.7004
Max Act: 1.5785. Min Act: -0.1700
Data Index: 1387729 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7004. Min Range: -1.7004
Max Act: 1.5959. Min Act: -0.1700
Data Index: 7340139 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7004. Min Range: -1.7004
Max Act: 1.5785. Min Act: -0.1700
Data Index: 2533139 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7004. Min Range: -1.7004
Max Act: 1.5785. Min Act: -0.1700
Data Index: 8712559 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7004. Min Range: -1.7004
Max Act: 1.5610. Min Act: -0.1700
Data Index: 3087378 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7004. Min Range: -1.7004
Max Act: 1.5610. Min Act: -0.1700
Data Index: 6898665 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7004. Min Range: -1.7004
Max Act: 1.5435. Min Act: -0.1700
Data Index: 4332257 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7004. Min Range: -1.7004
Max Act: 1.5435. Min Act: -0.1700
Data Index: 8809244 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7004. Min Range: -1.7004
Max Act: 1.5610. Min Act: -0.1700
Data Index: 4369458 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7004. Min Range: -1.7004
Max Act: 1.5259. Min Act: -0.1700
Data Index: 8256328 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7004. Min Range: -1.7004
Max Act: 1.5259. Min Act: -0.1700
Data Index: 3865323 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7004. Min Range: -1.7004
Max Act: 1.5259. Min Act: -0.1700
Data Index: 6125444 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7004. Min Range: -1.7004
Max Act: 1.5084. Min Act: -0.1700
Data Index: 5176027 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7004. Min Range: -1.7004
Max Act: 1.5084. Min Act: -0.1700
Data Index: 1527515 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7004. Min Range: -1.7004
Max Act: 1.5259. Min Act: -0.1700
Data Index: 3954469 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7004. Min Range: -1.7004
Max Act: 1.5259. Min Act: -0.1700
Data Index: 930551 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19