Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2725 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1529. Min Range: -4.1529
Max Act: 4.1529. Min Act: -0.1700
Data Index: 7361042 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1529. Min Range: -4.1529
Max Act: 4.0591. Min Act: -0.1700
Data Index: 4969290 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1529. Min Range: -4.1529
Max Act: 4.0591. Min Act: -0.1700
Data Index: 7641341 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1529. Min Range: -4.1529
Max Act: 4.0279. Min Act: -0.1700
Data Index: 4126596 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1529. Min Range: -4.1529
Max Act: 4.0279. Min Act: -0.1700
Data Index: 4219338 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1529. Min Range: -4.1529
Max Act: 4.0279. Min Act: -0.1700
Data Index: 3734057 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1529. Min Range: -4.1529
Max Act: 3.9966. Min Act: -0.1700
Data Index: 3887142 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1529. Min Range: -4.1529
Max Act: 3.9966. Min Act: -0.1700
Data Index: 3145035 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1529. Min Range: -4.1529
Max Act: 3.9966. Min Act: -0.1700
Data Index: 3788934 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1529. Min Range: -4.1529
Max Act: 3.9966. Min Act: -0.1700
Data Index: 4798186 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1529. Min Range: -4.1529
Max Act: 3.9966. Min Act: -0.1700
Data Index: 8828883 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1529. Min Range: -4.1529
Max Act: 3.9966. Min Act: -0.1700
Data Index: 7917136 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1529. Min Range: -4.1529
Max Act: 3.9966. Min Act: -0.1700
Data Index: 7762564 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1529. Min Range: -4.1529
Max Act: 3.9966. Min Act: -0.1700
Data Index: 5071741 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1529. Min Range: -4.1529
Max Act: 3.9966. Min Act: -0.1700
Data Index: 7517298 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1529. Min Range: -4.1529
Max Act: 3.9966. Min Act: -0.1700
Data Index: 5317230 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1529. Min Range: -4.1529
Max Act: 3.9966. Min Act: -0.1700
Data Index: 6942150 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1529. Min Range: -4.1529
Max Act: 3.9966. Min Act: -0.1700
Data Index: 4195391 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1529. Min Range: -4.1529
Max Act: 3.9966. Min Act: -0.1700
Data Index: 6305611 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1529. Min Range: -4.1529
Max Act: 3.9966. Min Act: -0.1700
Data Index: 505286 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19