Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2184 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.7150. Min Range: -0.7150
Max Act: 0.7150. Min Act: -0.1700
Data Index: 8714697 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7150. Min Range: -0.7150
Max Act: 0.7068. Min Act: -0.1700
Data Index: 1467761 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7150. Min Range: -0.7150
Max Act: 0.7068. Min Act: -0.1700
Data Index: 1613098 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7150. Min Range: -0.7150
Max Act: 0.6986. Min Act: -0.1700
Data Index: 3482248 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7150. Min Range: -0.7150
Max Act: 0.6823. Min Act: -0.1700
Data Index: 7680423 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7150. Min Range: -0.7150
Max Act: 0.6986. Min Act: -0.1700
Data Index: 3722212 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7150. Min Range: -0.7150
Max Act: 0.6742. Min Act: -0.1700
Data Index: 8017280 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7150. Min Range: -0.7150
Max Act: 0.6742. Min Act: -0.1700
Data Index: 7466360 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7150. Min Range: -0.7150
Max Act: 0.6742. Min Act: -0.1700
Data Index: 4849020 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7150. Min Range: -0.7150
Max Act: 0.6742. Min Act: -0.1700
Data Index: 6252471 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7150. Min Range: -0.7150
Max Act: 0.6581. Min Act: -0.1700
Data Index: 3238966 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7150. Min Range: -0.7150
Max Act: 0.6662. Min Act: -0.1699
Data Index: 942352 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7150. Min Range: -0.7150
Max Act: 0.6662. Min Act: -0.1700
Data Index: 1436759 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7150. Min Range: -0.7150
Max Act: 0.6581. Min Act: -0.1700
Data Index: 1449788 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7150. Min Range: -0.7150
Max Act: 0.6581. Min Act: -0.1700
Data Index: 5071883 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7150. Min Range: -0.7150
Max Act: 0.6501. Min Act: -0.1698
Data Index: 2439566 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7150. Min Range: -0.7150
Max Act: 0.6501. Min Act: -0.1700
Data Index: 7683929 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7150. Min Range: -0.7150
Max Act: 0.6501. Min Act: -0.1700
Data Index: 3105963 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7150. Min Range: -0.7150
Max Act: 0.6501. Min Act: -0.1700
Data Index: 5445791 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7150. Min Range: -0.7150
Max Act: 0.6501. Min Act: -0.1700
Data Index: 876608 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19