Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3709 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9516. Min Range: -7.9516
Max Act: 7.9516. Min Act: -0.1700
Data Index: 2466313 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9516. Min Range: -7.9516
Max Act: 7.8578. Min Act: -0.1700
Data Index: 6458692 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9516. Min Range: -7.9516
Max Act: 7.5766. Min Act: -0.1700
Data Index: 1678287 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9516. Min Range: -7.9516
Max Act: 7.4828. Min Act: -0.1700
Data Index: 8370120 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9516. Min Range: -7.9516
Max Act: 7.3891. Min Act: -0.1700
Data Index: 2943481 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9516. Min Range: -7.9516
Max Act: 7.2328. Min Act: -0.1700
Data Index: 7638267 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9516. Min Range: -7.9516
Max Act: 7.1078. Min Act: -0.1700
Data Index: 4551459 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9516. Min Range: -7.9516
Max Act: 7.1078. Min Act: -0.1700
Data Index: 684533 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9516. Min Range: -7.9516
Max Act: 7.1078. Min Act: -0.1700
Data Index: 5501764 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9516. Min Range: -7.9516
Max Act: 7.0453. Min Act: -0.1700
Data Index: 2417787 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9516. Min Range: -7.9516
Max Act: 6.9516. Min Act: -0.1700
Data Index: 2615515 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9516. Min Range: -7.9516
Max Act: 6.9516. Min Act: -0.1700
Data Index: 5575872 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9516. Min Range: -7.9516
Max Act: 6.9203. Min Act: -0.1700
Data Index: 2061596 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9516. Min Range: -7.9516
Max Act: 6.8891. Min Act: -0.1700
Data Index: 788695 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9516. Min Range: -7.9516
Max Act: 6.8891. Min Act: -0.1700
Data Index: 4891232 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9516. Min Range: -7.9516
Max Act: 6.8578. Min Act: -0.1700
Data Index: 8138351 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9516. Min Range: -7.9516
Max Act: 6.8266. Min Act: -0.1700
Data Index: 1894260 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9516. Min Range: -7.9516
Max Act: 6.8266. Min Act: -0.1700
Data Index: 7310643 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9516. Min Range: -7.9516
Max Act: 6.7953. Min Act: -0.1700
Data Index: 6258466 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9516. Min Range: -7.9516
Max Act: 6.7953. Min Act: -0.1700
Data Index: 1887521 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #19