Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3957 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0204. Min Range: -5.0204
Max Act: 5.0204. Min Act: -0.1700
Data Index: 1149866 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0204. Min Range: -5.0204
Max Act: 4.9579. Min Act: -0.1700
Data Index: 3652534 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0204. Min Range: -5.0204
Max Act: 4.9579. Min Act: -0.1700
Data Index: 1619708 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0204. Min Range: -5.0204
Max Act: 4.8641. Min Act: -0.1700
Data Index: 6939280 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0204. Min Range: -5.0204
Max Act: 4.8016. Min Act: -0.1700
Data Index: 5488691 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0204. Min Range: -5.0204
Max Act: 4.8016. Min Act: -0.1700
Data Index: 4992659 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0204. Min Range: -5.0204
Max Act: 4.8016. Min Act: -0.1700
Data Index: 5804856 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0204. Min Range: -5.0204
Max Act: 4.7704. Min Act: -0.1700
Data Index: 6890711 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0204. Min Range: -5.0204
Max Act: 4.7391. Min Act: -0.1700
Data Index: 4985566 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0204. Min Range: -5.0204
Max Act: 4.7391. Min Act: -0.1700
Data Index: 8750173 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0204. Min Range: -5.0204
Max Act: 4.7391. Min Act: -0.1700
Data Index: 3721596 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0204. Min Range: -5.0204
Max Act: 4.7391. Min Act: -0.1700
Data Index: 8549024 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0204. Min Range: -5.0204
Max Act: 4.7391. Min Act: -0.1700
Data Index: 6430032 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0204. Min Range: -5.0204
Max Act: 4.7391. Min Act: -0.1700
Data Index: 5928380 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0204. Min Range: -5.0204
Max Act: 4.7079. Min Act: -0.1700
Data Index: 6521423 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0204. Min Range: -5.0204
Max Act: 4.7079. Min Act: -0.1700
Data Index: 1619711 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0204. Min Range: -5.0204
Max Act: 4.7079. Min Act: -0.1700
Data Index: 1284592 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0204. Min Range: -5.0204
Max Act: 4.7079. Min Act: -0.1700
Data Index: 4054161 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0204. Min Range: -5.0204
Max Act: 4.6766. Min Act: -0.1700
Data Index: 7517836 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0204. Min Range: -5.0204
Max Act: 4.6766. Min Act: -0.1700
Data Index: 4384759 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19