Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1128 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8870. Min Range: -7.8870
Max Act: 7.8870. Min Act: -0.1700
Data Index: 5200865 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8870. Min Range: -7.8870
Max Act: 7.8557. Min Act: -0.1700
Data Index: 2471292 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8870. Min Range: -7.8870
Max Act: 7.5745. Min Act: -0.1700
Data Index: 1464470 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8870. Min Range: -7.8870
Max Act: 7.4807. Min Act: -0.1700
Data Index: 6254940 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8870. Min Range: -7.8870
Max Act: 7.4807. Min Act: -0.1700
Data Index: 8250078 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8870. Min Range: -7.8870
Max Act: 7.4807. Min Act: -0.1700
Data Index: 7510961 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8870. Min Range: -7.8870
Max Act: 7.4182. Min Act: -0.1700
Data Index: 4122961 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8870. Min Range: -7.8870
Max Act: 7.3870. Min Act: -0.1700
Data Index: 6480314 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8870. Min Range: -7.8870
Max Act: 7.3557. Min Act: -0.1700
Data Index: 4089010 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8870. Min Range: -7.8870
Max Act: 7.3245. Min Act: -0.1700
Data Index: 832317 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8870. Min Range: -7.8870
Max Act: 7.3245. Min Act: -0.1700
Data Index: 7010100 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8870. Min Range: -7.8870
Max Act: 7.2307. Min Act: -0.1700
Data Index: 6026512 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8870. Min Range: -7.8870
Max Act: 7.2307. Min Act: -0.1700
Data Index: 7735233 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8870. Min Range: -7.8870
Max Act: 7.2307. Min Act: -0.1700
Data Index: 2203051 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8870. Min Range: -7.8870
Max Act: 7.2307. Min Act: -0.1700
Data Index: 3458051 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8870. Min Range: -7.8870
Max Act: 7.1370. Min Act: -0.1700
Data Index: 3451830 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8870. Min Range: -7.8870
Max Act: 7.1682. Min Act: -0.1700
Data Index: 256188 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8870. Min Range: -7.8870
Max Act: 7.1370. Min Act: -0.1700
Data Index: 3307149 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8870. Min Range: -7.8870
Max Act: 7.1057. Min Act: -0.1700
Data Index: 1971150 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8870. Min Range: -7.8870
Max Act: 7.0745. Min Act: -0.1700
Data Index: 1874814 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #19