Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2825 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5835. Min Range: -8.5835
Max Act: 8.5835. Min Act: -0.1700
Data Index: 3254412 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5835. Min Range: -8.5835
Max Act: 8.5835. Min Act: -0.1700
Data Index: 2779408 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5835. Min Range: -8.5835
Max Act: 8.5210. Min Act: -0.1700
Data Index: 6477472 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5835. Min Range: -8.5835
Max Act: 8.2710. Min Act: -0.1700
Data Index: 4551839 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5835. Min Range: -8.5835
Max Act: 8.0835. Min Act: -0.1700
Data Index: 6872517 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5835. Min Range: -8.5835
Max Act: 8.0835. Min Act: -0.1700
Data Index: 7754930 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5835. Min Range: -8.5835
Max Act: 8.0210. Min Act: -0.1700
Data Index: 2839355 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5835. Min Range: -8.5835
Max Act: 8.0210. Min Act: -0.1700
Data Index: 6905463 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5835. Min Range: -8.5835
Max Act: 7.9585. Min Act: -0.1700
Data Index: 2494142 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5835. Min Range: -8.5835
Max Act: 7.8960. Min Act: -0.1700
Data Index: 4846650 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5835. Min Range: -8.5835
Max Act: 7.8335. Min Act: -0.1700
Data Index: 5886490 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5835. Min Range: -8.5835
Max Act: 7.8960. Min Act: -0.1700
Data Index: 906349 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5835. Min Range: -8.5835
Max Act: 7.8960. Min Act: -0.1700
Data Index: 2931887 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5835. Min Range: -8.5835
Max Act: 7.8335. Min Act: -0.1700
Data Index: 7146435 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5835. Min Range: -8.5835
Max Act: 7.8335. Min Act: -0.1700
Data Index: 103714 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5835. Min Range: -8.5835
Max Act: 7.8335. Min Act: -0.1700
Data Index: 3564007 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5835. Min Range: -8.5835
Max Act: 7.8335. Min Act: -0.1700
Data Index: 6847105 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5835. Min Range: -8.5835
Max Act: 7.7710. Min Act: -0.1700
Data Index: 1834258 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5835. Min Range: -8.5835
Max Act: 7.7710. Min Act: -0.1700
Data Index: 2331537 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5835. Min Range: -8.5835
Max Act: 7.7710. Min Act: -0.1700
Data Index: 5283345 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19