Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1395 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1301. Min Range: -4.1301
Max Act: 4.1301. Min Act: -0.1700
Data Index: 1732503 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1301. Min Range: -4.1301
Max Act: 4.0364. Min Act: -0.1700
Data Index: 4357006 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1301. Min Range: -4.1301
Max Act: 4.0364. Min Act: -0.1700
Data Index: 4897155 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1301. Min Range: -4.1301
Max Act: 4.0051. Min Act: -0.1700
Data Index: 3586572 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1301. Min Range: -4.1301
Max Act: 4.0051. Min Act: -0.1700
Data Index: 8115984 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1301. Min Range: -4.1301
Max Act: 3.9738. Min Act: -0.1700
Data Index: 3076042 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1301. Min Range: -4.1301
Max Act: 3.9738. Min Act: -0.1700
Data Index: 3974834 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1301. Min Range: -4.1301
Max Act: 3.9738. Min Act: -0.1700
Data Index: 8259403 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1301. Min Range: -4.1301
Max Act: 3.9738. Min Act: -0.1700
Data Index: 8050535 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1301. Min Range: -4.1301
Max Act: 4.0051. Min Act: -0.1700
Data Index: 2211869 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1301. Min Range: -4.1301
Max Act: 3.9738. Min Act: -0.1700
Data Index: 5071750 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1301. Min Range: -4.1301
Max Act: 3.9426. Min Act: -0.1700
Data Index: 7367961 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1301. Min Range: -4.1301
Max Act: 3.9426. Min Act: -0.1700
Data Index: 2170060 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1301. Min Range: -4.1301
Max Act: 3.9426. Min Act: -0.1700
Data Index: 6572569 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1301. Min Range: -4.1301
Max Act: 3.9426. Min Act: -0.1700
Data Index: 5823863 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1301. Min Range: -4.1301
Max Act: 3.9426. Min Act: -0.1700
Data Index: 5393500 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1301. Min Range: -4.1301
Max Act: 3.9113. Min Act: -0.1700
Data Index: 4843805 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1301. Min Range: -4.1301
Max Act: 3.9426. Min Act: -0.1700
Data Index: 1028773 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1301. Min Range: -4.1301
Max Act: 3.9426. Min Act: -0.1700
Data Index: 4651327 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1301. Min Range: -4.1301
Max Act: 3.9426. Min Act: -0.1700
Data Index: 4523225 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19