Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3088 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5835. Min Range: -7.5835
Max Act: 7.5835. Min Act: -0.1700
Data Index: 8502039 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5835. Min Range: -7.5835
Max Act: 7.4585. Min Act: -0.1700
Data Index: 8196360 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5835. Min Range: -7.5835
Max Act: 7.4898. Min Act: -0.1700
Data Index: 15423 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5835. Min Range: -7.5835
Max Act: 7.3023. Min Act: -0.1700
Data Index: 3590146 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5835. Min Range: -7.5835
Max Act: 7.2710. Min Act: -0.1700
Data Index: 3640053 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5835. Min Range: -7.5835
Max Act: 7.2710. Min Act: -0.1700
Data Index: 5876828 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5835. Min Range: -7.5835
Max Act: 7.2398. Min Act: -0.1700
Data Index: 2622376 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5835. Min Range: -7.5835
Max Act: 7.2085. Min Act: -0.1700
Data Index: 3397480 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5835. Min Range: -7.5835
Max Act: 7.1773. Min Act: -0.1700
Data Index: 6750864 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5835. Min Range: -7.5835
Max Act: 7.1148. Min Act: -0.1700
Data Index: 7563661 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5835. Min Range: -7.5835
Max Act: 7.1148. Min Act: -0.1700
Data Index: 142981 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5835. Min Range: -7.5835
Max Act: 7.1148. Min Act: -0.1700
Data Index: 8196359 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5835. Min Range: -7.5835
Max Act: 7.0210. Min Act: -0.1700
Data Index: 4331094 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5835. Min Range: -7.5835
Max Act: 6.9898. Min Act: -0.1700
Data Index: 2622375 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5835. Min Range: -7.5835
Max Act: 6.9898. Min Act: -0.1700
Data Index: 2653384 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5835. Min Range: -7.5835
Max Act: 6.8960. Min Act: -0.1700
Data Index: 6916553 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5835. Min Range: -7.5835
Max Act: 6.8648. Min Act: -0.1700
Data Index: 4602371 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5835. Min Range: -7.5835
Max Act: 6.8648. Min Act: -0.1700
Data Index: 1078100 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5835. Min Range: -7.5835
Max Act: 6.8648. Min Act: -0.1700
Data Index: 5876827 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5835. Min Range: -7.5835
Max Act: 6.8023. Min Act: -0.1700
Data Index: 1909698 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19