Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3847 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4007. Min Range: -3.4007
Max Act: 3.4007. Min Act: -0.1700
Data Index: 950299 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4007. Min Range: -3.4007
Max Act: 3.1494. Min Act: -0.1700
Data Index: 6413267 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4007. Min Range: -3.4007
Max Act: 3.1021. Min Act: -0.1700
Data Index: 2506996 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4007. Min Range: -3.4007
Max Act: 3.0863. Min Act: -0.1700
Data Index: 5456571 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4007. Min Range: -3.4007
Max Act: 3.0548. Min Act: -0.1700
Data Index: 5905208 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4007. Min Range: -3.4007
Max Act: 3.0390. Min Act: -0.1700
Data Index: 3576223 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4007. Min Range: -3.4007
Max Act: 3.0390. Min Act: -0.1700
Data Index: 3085608 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4007. Min Range: -3.4007
Max Act: 3.0232. Min Act: -0.1700
Data Index: 3782758 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4007. Min Range: -3.4007
Max Act: 3.0232. Min Act: -0.1700
Data Index: 1105801 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4007. Min Range: -3.4007
Max Act: 3.0232. Min Act: -0.1700
Data Index: 2220598 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4007. Min Range: -3.4007
Max Act: 3.0074. Min Act: -0.1700
Data Index: 2051639 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4007. Min Range: -3.4007
Max Act: 3.0390. Min Act: -0.1700
Data Index: 5817083 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4007. Min Range: -3.4007
Max Act: 3.0074. Min Act: -0.1700
Data Index: 6874842 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4007. Min Range: -3.4007
Max Act: 3.0074. Min Act: -0.1700
Data Index: 3473692 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4007. Min Range: -3.4007
Max Act: 3.0074. Min Act: -0.1700
Data Index: 7056328 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4007. Min Range: -3.4007
Max Act: 3.0074. Min Act: -0.1700
Data Index: 4937378 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4007. Min Range: -3.4007
Max Act: 3.0074. Min Act: -0.1700
Data Index: 7177763 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4007. Min Range: -3.4007
Max Act: 2.9916. Min Act: -0.1700
Data Index: 554177 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4007. Min Range: -3.4007
Max Act: 3.0074. Min Act: -0.1700
Data Index: 6767247 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4007. Min Range: -3.4007
Max Act: 2.9916. Min Act: -0.1700
Data Index: 1377281 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #19