Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3137 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2112. Min Range: -8.2112
Max Act: 8.2112. Min Act: -0.1700
Data Index: 591389 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2112. Min Range: -8.2112
Max Act: 8.1487. Min Act: -0.1700
Data Index: 2897596 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2112. Min Range: -8.2112
Max Act: 8.0237. Min Act: -0.1700
Data Index: 4156351 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2112. Min Range: -8.2112
Max Act: 7.9612. Min Act: -0.1700
Data Index: 8762798 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2112. Min Range: -8.2112
Max Act: 7.8987. Min Act: -0.1700
Data Index: 8013507 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2112. Min Range: -8.2112
Max Act: 7.9612. Min Act: -0.1700
Data Index: 3401145 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2112. Min Range: -8.2112
Max Act: 7.8987. Min Act: -0.1700
Data Index: 6913319 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2112. Min Range: -8.2112
Max Act: 7.8362. Min Act: -0.1700
Data Index: 7130618 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2112. Min Range: -8.2112
Max Act: 7.8987. Min Act: -0.1700
Data Index: 321286 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2112. Min Range: -8.2112
Max Act: 7.8362. Min Act: -0.1700
Data Index: 3816362 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2112. Min Range: -8.2112
Max Act: 7.8362. Min Act: -0.1700
Data Index: 3162080 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2112. Min Range: -8.2112
Max Act: 7.8362. Min Act: -0.1700
Data Index: 8539691 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2112. Min Range: -8.2112
Max Act: 7.8362. Min Act: -0.1700
Data Index: 1299676 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2112. Min Range: -8.2112
Max Act: 7.8362. Min Act: -0.1700
Data Index: 4949653 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2112. Min Range: -8.2112
Max Act: 7.7737. Min Act: -0.1700
Data Index: 6444588 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2112. Min Range: -8.2112
Max Act: 7.8362. Min Act: -0.1700
Data Index: 722016 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2112. Min Range: -8.2112
Max Act: 7.7112. Min Act: -0.1700
Data Index: 1040794 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2112. Min Range: -8.2112
Max Act: 7.7112. Min Act: -0.1700
Data Index: 6702476 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2112. Min Range: -8.2112
Max Act: 7.7112. Min Act: -0.1700
Data Index: 5002815 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2112. Min Range: -8.2112
Max Act: 7.7112. Min Act: -0.1700
Data Index: 6791593 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19