Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1848 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.2071. Min Act: -0.1700
Data Index: 4702364 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.2071. Min Act: -0.1700
Data Index: 1659745 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.1756. Min Act: -0.1700
Data Index: 5905219 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.1599. Min Act: -0.1700
Data Index: 8683304 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.1442. Min Act: -0.1700
Data Index: 7312262 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.1442. Min Act: -0.1700
Data Index: 3268247 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.1284. Min Act: -0.1700
Data Index: 1885055 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.1127. Min Act: -0.1700
Data Index: 2308476 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.0811. Min Act: -0.1700
Data Index: 7693173 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.0811. Min Act: -0.1700
Data Index: 7546072 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.0654. Min Act: -0.1700
Data Index: 5646463 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.0654. Min Act: -0.1700
Data Index: 7502527 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.0654. Min Act: -0.1700
Data Index: 6022831 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.0654. Min Act: -0.1700
Data Index: 8681858 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.0654. Min Act: -0.1700
Data Index: 8519297 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.0654. Min Act: -0.1700
Data Index: 1357729 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.0654. Min Act: -0.1700
Data Index: 2195964 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.0496. Min Act: -0.1700
Data Index: 141423 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.0496. Min Act: -0.1700
Data Index: 186547 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2071. Min Range: -3.2071
Max Act: 3.0496. Min Act: -0.1700
Data Index: 4816291 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19