Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4310 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4318. Min Range: -9.4318
Max Act: 9.4318. Min Act: -0.1700
Data Index: 3009765 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4318. Min Range: -9.4318
Max Act: 9.3693. Min Act: -0.1700
Data Index: 4327808 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4318. Min Range: -9.4318
Max Act: 9.3693. Min Act: -0.1700
Data Index: 5072953 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4318. Min Range: -9.4318
Max Act: 9.3068. Min Act: -0.1700
Data Index: 1104493 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4318. Min Range: -9.4318
Max Act: 9.2443. Min Act: -0.1700
Data Index: 1647479 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4318. Min Range: -9.4318
Max Act: 9.2443. Min Act: -0.1700
Data Index: 8591018 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4318. Min Range: -9.4318
Max Act: 9.2443. Min Act: -0.1700
Data Index: 1187099 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4318. Min Range: -9.4318
Max Act: 9.2443. Min Act: -0.1700
Data Index: 1000644 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4318. Min Range: -9.4318
Max Act: 9.1818. Min Act: -0.1700
Data Index: 6358202 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4318. Min Range: -9.4318
Max Act: 8.9943. Min Act: -0.1700
Data Index: 1373363 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4318. Min Range: -9.4318
Max Act: 8.9943. Min Act: -0.1700
Data Index: 1619262 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4318. Min Range: -9.4318
Max Act: 8.8693. Min Act: -0.1700
Data Index: 7584337 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4318. Min Range: -9.4318
Max Act: 8.9318. Min Act: -0.1700
Data Index: 1346021 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4318. Min Range: -9.4318
Max Act: 8.9318. Min Act: -0.1700
Data Index: 8312328 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4318. Min Range: -9.4318
Max Act: 8.8693. Min Act: -0.1700
Data Index: 3330382 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4318. Min Range: -9.4318
Max Act: 8.8693. Min Act: -0.1700
Data Index: 570826 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4318. Min Range: -9.4318
Max Act: 8.8693. Min Act: -0.1700
Data Index: 4978132 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4318. Min Range: -9.4318
Max Act: 8.8068. Min Act: -0.1700
Data Index: 6334872 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4318. Min Range: -9.4318
Max Act: 8.8068. Min Act: -0.1700
Data Index: 5724905 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4318. Min Range: -9.4318
Max Act: 8.7443. Min Act: -0.1700
Data Index: 4731443 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #19