Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5854 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2734. Min Range: -6.2734
Max Act: 6.2734. Min Act: -0.1700
Data Index: 2669412 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2734. Min Range: -6.2734
Max Act: 6.2109. Min Act: -0.1700
Data Index: 2647837 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2734. Min Range: -6.2734
Max Act: 6.1484. Min Act: -0.1700
Data Index: 5749084 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2734. Min Range: -6.2734
Max Act: 6.1171. Min Act: -0.1700
Data Index: 984011 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2734. Min Range: -6.2734
Max Act: 6.0859. Min Act: -0.1700
Data Index: 1107853 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2734. Min Range: -6.2734
Max Act: 6.0859. Min Act: -0.1700
Data Index: 5088190 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2734. Min Range: -6.2734
Max Act: 5.8984. Min Act: -0.1700
Data Index: 244621 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2734. Min Range: -6.2734
Max Act: 5.8671. Min Act: -0.1700
Data Index: 8400857 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2734. Min Range: -6.2734
Max Act: 5.8671. Min Act: -0.1700
Data Index: 287173 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2734. Min Range: -6.2734
Max Act: 5.8046. Min Act: -0.1700
Data Index: 4904400 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2734. Min Range: -6.2734
Max Act: 5.8046. Min Act: -0.1700
Data Index: 7062278 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2734. Min Range: -6.2734
Max Act: 5.7734. Min Act: -0.1700
Data Index: 1818116 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2734. Min Range: -6.2734
Max Act: 5.7421. Min Act: -0.1700
Data Index: 598382 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2734. Min Range: -6.2734
Max Act: 5.7421. Min Act: -0.1700
Data Index: 7555655 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2734. Min Range: -6.2734
Max Act: 5.7421. Min Act: -0.1700
Data Index: 8507895 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2734. Min Range: -6.2734
Max Act: 5.7421. Min Act: -0.1700
Data Index: 3320392 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2734. Min Range: -6.2734
Max Act: 5.7109. Min Act: -0.1700
Data Index: 2139652 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2734. Min Range: -6.2734
Max Act: 5.6796. Min Act: -0.1700
Data Index: 4760089 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2734. Min Range: -6.2734
Max Act: 5.6796. Min Act: -0.1700
Data Index: 1181223 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2734. Min Range: -6.2734
Max Act: 5.6484. Min Act: -0.1700
Data Index: 3913639 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19