Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 996 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7268. Min Range: -2.7268
Max Act: 2.7268. Min Act: -0.1700
Data Index: 1920404 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7268. Min Range: -2.7268
Max Act: 2.7268. Min Act: -0.1700
Data Index: 1271664 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7268. Min Range: -2.7268
Max Act: 2.7268. Min Act: -0.1700
Data Index: 4954867 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7268. Min Range: -2.7268
Max Act: 2.7108. Min Act: -0.1700
Data Index: 7119221 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7268. Min Range: -2.7268
Max Act: 2.7108. Min Act: -0.1700
Data Index: 3012990 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7268. Min Range: -2.7268
Max Act: 2.6948. Min Act: -0.1700
Data Index: 276987 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7268. Min Range: -2.7268
Max Act: 2.7108. Min Act: -0.1700
Data Index: 4795338 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7268. Min Range: -2.7268
Max Act: 2.6948. Min Act: -0.1700
Data Index: 4512723 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7268. Min Range: -2.7268
Max Act: 2.6948. Min Act: -0.1700
Data Index: 8610091 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7268. Min Range: -2.7268
Max Act: 2.6948. Min Act: -0.1700
Data Index: 8355883 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7268. Min Range: -2.7268
Max Act: 2.6948. Min Act: -0.1700
Data Index: 8352345 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7268. Min Range: -2.7268
Max Act: 2.6948. Min Act: -0.1700
Data Index: 7752770 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7268. Min Range: -2.7268
Max Act: 2.6948. Min Act: -0.1700
Data Index: 7701216 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7268. Min Range: -2.7268
Max Act: 2.6948. Min Act: -0.1700
Data Index: 2732558 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7268. Min Range: -2.7268
Max Act: 2.6948. Min Act: -0.1700
Data Index: 2575058 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7268. Min Range: -2.7268
Max Act: 2.6948. Min Act: -0.1700
Data Index: 6453548 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7268. Min Range: -2.7268
Max Act: 2.6948. Min Act: -0.1700
Data Index: 670039 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7268. Min Range: -2.7268
Max Act: 2.6948. Min Act: -0.1700
Data Index: 1773715 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7268. Min Range: -2.7268
Max Act: 2.6788. Min Act: -0.1700
Data Index: 4155783 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7268. Min Range: -2.7268
Max Act: 2.6788. Min Act: -0.1700
Data Index: 4849440 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19