Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5044 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6410. Min Range: -2.6410
Max Act: 2.6410. Min Act: -0.1700
Data Index: 2666996 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6410. Min Range: -2.6410
Max Act: 2.6250. Min Act: -0.1700
Data Index: 3193749 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6410. Min Range: -2.6410
Max Act: 2.6250. Min Act: -0.1700
Data Index: 7089979 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6410. Min Range: -2.6410
Max Act: 2.6250. Min Act: -0.1700
Data Index: 1679764 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6410. Min Range: -2.6410
Max Act: 2.6250. Min Act: -0.1700
Data Index: 7055091 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6410. Min Range: -2.6410
Max Act: 2.6250. Min Act: -0.1700
Data Index: 6910428 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6410. Min Range: -2.6410
Max Act: 2.5928. Min Act: -0.1700
Data Index: 3812681 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6410. Min Range: -2.6410
Max Act: 2.6089. Min Act: -0.1700
Data Index: 8363228 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6410. Min Range: -2.6410
Max Act: 2.5928. Min Act: -0.1700
Data Index: 7009837 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6410. Min Range: -2.6410
Max Act: 2.5928. Min Act: -0.1700
Data Index: 6605742 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6410. Min Range: -2.6410
Max Act: 2.5767. Min Act: -0.1700
Data Index: 8029875 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6410. Min Range: -2.6410
Max Act: 2.5928. Min Act: -0.1700
Data Index: 3540473 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6410. Min Range: -2.6410
Max Act: 2.5767. Min Act: -0.1700
Data Index: 7426097 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6410. Min Range: -2.6410
Max Act: 2.5606. Min Act: -0.1700
Data Index: 5749096 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6410. Min Range: -2.6410
Max Act: 2.5606. Min Act: -0.1700
Data Index: 7838909 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6410. Min Range: -2.6410
Max Act: 2.5606. Min Act: -0.1700
Data Index: 2030432 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6410. Min Range: -2.6410
Max Act: 2.5606. Min Act: -0.1700
Data Index: 1263252 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6410. Min Range: -2.6410
Max Act: 2.5606. Min Act: -0.1700
Data Index: 2355132 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6410. Min Range: -2.6410
Max Act: 2.5444. Min Act: -0.1700
Data Index: 39302 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6410. Min Range: -2.6410
Max Act: 2.5444. Min Act: -0.1700
Data Index: 7884072 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19