Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5939 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.6870. Min Act: -0.1700
Data Index: 516218 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.4995. Min Act: -0.1700
Data Index: 6558250 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.4058. Min Act: -0.1700
Data Index: 7524975 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.4058. Min Act: -0.1700
Data Index: 6099327 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.3745. Min Act: -0.1700
Data Index: 197694 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.3433. Min Act: -0.1700
Data Index: 4029773 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.2808. Min Act: -0.1700
Data Index: 512134 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.2808. Min Act: -0.1700
Data Index: 2194297 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.2183. Min Act: -0.1700
Data Index: 2958893 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.2183. Min Act: -0.1700
Data Index: 5947969 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.2183. Min Act: -0.1700
Data Index: 5530245 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.2183. Min Act: -0.1700
Data Index: 1274967 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.2183. Min Act: -0.1700
Data Index: 1331473 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.1870. Min Act: -0.1700
Data Index: 5707768 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.1870. Min Act: -0.1700
Data Index: 4812843 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.1870. Min Act: -0.1700
Data Index: 4359294 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.1870. Min Act: -0.1700
Data Index: 4138500 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.1870. Min Act: -0.1700
Data Index: 5599172 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.1870. Min Act: -0.1700
Data Index: 3382791 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.1870. Min Act: -0.1700
Data Index: 7521205 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #19