Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6041 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5539. Min Range: -6.5539
Max Act: 6.5539. Min Act: -0.1700
Data Index: 8164791 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5539. Min Range: -6.5539
Max Act: 6.3664. Min Act: -0.1700
Data Index: 779031 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5539. Min Range: -6.5539
Max Act: 6.2726. Min Act: -0.1700
Data Index: 6648119 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5539. Min Range: -6.5539
Max Act: 6.2726. Min Act: -0.1700
Data Index: 8466718 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5539. Min Range: -6.5539
Max Act: 6.2726. Min Act: -0.1700
Data Index: 3593963 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5539. Min Range: -6.5539
Max Act: 6.3039. Min Act: -0.1700
Data Index: 6552129 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5539. Min Range: -6.5539
Max Act: 6.2726. Min Act: -0.1700
Data Index: 5369373 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5539. Min Range: -6.5539
Max Act: 6.1789. Min Act: -0.1700
Data Index: 6938623 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5539. Min Range: -6.5539
Max Act: 6.2101. Min Act: -0.1700
Data Index: 1521780 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5539. Min Range: -6.5539
Max Act: 6.2101. Min Act: -0.1700
Data Index: 343441 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5539. Min Range: -6.5539
Max Act: 6.1476. Min Act: -0.1700
Data Index: 6406573 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5539. Min Range: -6.5539
Max Act: 6.1789. Min Act: -0.1700
Data Index: 2745872 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5539. Min Range: -6.5539
Max Act: 6.1789. Min Act: -0.1700
Data Index: 8226439 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5539. Min Range: -6.5539
Max Act: 6.1789. Min Act: -0.1700
Data Index: 7041709 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5539. Min Range: -6.5539
Max Act: 6.1789. Min Act: -0.1700
Data Index: 3369709 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5539. Min Range: -6.5539
Max Act: 6.1164. Min Act: -0.1700
Data Index: 2673466 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5539. Min Range: -6.5539
Max Act: 6.1164. Min Act: -0.1700
Data Index: 693498 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5539. Min Range: -6.5539
Max Act: 6.1164. Min Act: -0.1700
Data Index: 4501813 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5539. Min Range: -6.5539
Max Act: 6.0851. Min Act: -0.1700
Data Index: 96432 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5539. Min Range: -6.5539
Max Act: 6.1164. Min Act: -0.1700
Data Index: 5411075 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #19