Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3876 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1989. Min Range: -7.1989
Max Act: 7.1989. Min Act: -0.1700
Data Index: 207929 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1989. Min Range: -7.1989
Max Act: 7.1051. Min Act: -0.1700
Data Index: 1512959 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1989. Min Range: -7.1989
Max Act: 7.0739. Min Act: -0.1700
Data Index: 6203102 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1989. Min Range: -7.1989
Max Act: 7.0739. Min Act: -0.1700
Data Index: 3673493 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1989. Min Range: -7.1989
Max Act: 6.9801. Min Act: -0.1700
Data Index: 1121665 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1989. Min Range: -7.1989
Max Act: 6.9801. Min Act: -0.1700
Data Index: 4410446 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1989. Min Range: -7.1989
Max Act: 6.9489. Min Act: -0.1700
Data Index: 6827106 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1989. Min Range: -7.1989
Max Act: 6.9801. Min Act: -0.1700
Data Index: 1471159 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1989. Min Range: -7.1989
Max Act: 6.9801. Min Act: -0.1700
Data Index: 6473788 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1989. Min Range: -7.1989
Max Act: 6.9801. Min Act: -0.1700
Data Index: 3980201 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1989. Min Range: -7.1989
Max Act: 6.9801. Min Act: -0.1700
Data Index: 5698314 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1989. Min Range: -7.1989
Max Act: 6.9176. Min Act: -0.1700
Data Index: 991788 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1989. Min Range: -7.1989
Max Act: 6.8551. Min Act: -0.1700
Data Index: 4160671 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1989. Min Range: -7.1989
Max Act: 6.8239. Min Act: -0.1700
Data Index: 6815193 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1989. Min Range: -7.1989
Max Act: 6.7926. Min Act: -0.1700
Data Index: 6470215 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1989. Min Range: -7.1989
Max Act: 6.7614. Min Act: -0.1700
Data Index: 170955 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1989. Min Range: -7.1989
Max Act: 6.7926. Min Act: -0.1700
Data Index: 1873236 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1989. Min Range: -7.1989
Max Act: 6.7614. Min Act: -0.1700
Data Index: 3304617 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1989. Min Range: -7.1989
Max Act: 6.7614. Min Act: -0.1700
Data Index: 6200250 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1989. Min Range: -7.1989
Max Act: 6.7614. Min Act: -0.1700
Data Index: 4135003 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #19