Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4755 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6096. Min Range: -5.6096
Max Act: 5.6096. Min Act: -0.1700
Data Index: 4504723 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6096. Min Range: -5.6096
Max Act: 5.6096. Min Act: -0.1700
Data Index: 7993548 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6096. Min Range: -5.6096
Max Act: 5.5471. Min Act: -0.1700
Data Index: 7950775 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6096. Min Range: -5.6096
Max Act: 5.5159. Min Act: -0.1700
Data Index: 5301063 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6096. Min Range: -5.6096
Max Act: 5.4846. Min Act: -0.1700
Data Index: 2851977 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6096. Min Range: -5.6096
Max Act: 5.4846. Min Act: -0.1700
Data Index: 6200194 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6096. Min Range: -5.6096
Max Act: 5.4846. Min Act: -0.1700
Data Index: 4136537 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6096. Min Range: -5.6096
Max Act: 5.4534. Min Act: -0.1700
Data Index: 612005 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6096. Min Range: -5.6096
Max Act: 5.4534. Min Act: -0.1700
Data Index: 4056345 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6096. Min Range: -5.6096
Max Act: 5.4221. Min Act: -0.1700
Data Index: 1978281 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6096. Min Range: -5.6096
Max Act: 5.3909. Min Act: -0.1700
Data Index: 3654140 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6096. Min Range: -5.6096
Max Act: 5.3909. Min Act: -0.1700
Data Index: 1256109 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6096. Min Range: -5.6096
Max Act: 5.3909. Min Act: -0.1700
Data Index: 2920302 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6096. Min Range: -5.6096
Max Act: 5.2971. Min Act: -0.1700
Data Index: 552219 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6096. Min Range: -5.6096
Max Act: 5.3284. Min Act: -0.1700
Data Index: 146640 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6096. Min Range: -5.6096
Max Act: 5.2659. Min Act: -0.1700
Data Index: 810388 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6096. Min Range: -5.6096
Max Act: 5.2034. Min Act: -0.1700
Data Index: 5911413 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6096. Min Range: -5.6096
Max Act: 5.2034. Min Act: -0.1700
Data Index: 5465959 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6096. Min Range: -5.6096
Max Act: 5.2034. Min Act: -0.1700
Data Index: 3208986 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6096. Min Range: -5.6096
Max Act: 5.1721. Min Act: -0.1700
Data Index: 7752145 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19