Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3745 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4247. Min Range: -7.4247
Max Act: 7.3935. Min Act: -0.1700
Data Index: 6053694 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4247. Min Range: -7.4247
Max Act: 7.4247. Min Act: -0.1700
Data Index: 5473957 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4247. Min Range: -7.4247
Max Act: 7.3935. Min Act: -0.1700
Data Index: 3256972 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4247. Min Range: -7.4247
Max Act: 7.3935. Min Act: -0.1700
Data Index: 6525913 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4247. Min Range: -7.4247
Max Act: 7.2685. Min Act: -0.1700
Data Index: 841074 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4247. Min Range: -7.4247
Max Act: 7.2372. Min Act: -0.1700
Data Index: 5961339 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4247. Min Range: -7.4247
Max Act: 7.1747. Min Act: -0.1700
Data Index: 841079 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4247. Min Range: -7.4247
Max Act: 7.1435. Min Act: -0.1700
Data Index: 805770 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4247. Min Range: -7.4247
Max Act: 7.1122. Min Act: -0.1700
Data Index: 6755724 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4247. Min Range: -7.4247
Max Act: 7.0810. Min Act: -0.1700
Data Index: 5560955 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4247. Min Range: -7.4247
Max Act: 7.0185. Min Act: -0.1700
Data Index: 601457 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4247. Min Range: -7.4247
Max Act: 7.0497. Min Act: -0.1697
Data Index: 4413951 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4247. Min Range: -7.4247
Max Act: 7.0497. Min Act: -0.1700
Data Index: 1439281 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4247. Min Range: -7.4247
Max Act: 6.9872. Min Act: -0.1700
Data Index: 6984794 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4247. Min Range: -7.4247
Max Act: 7.0185. Min Act: -0.1700
Data Index: 8255925 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4247. Min Range: -7.4247
Max Act: 6.9872. Min Act: -0.1700
Data Index: 2035466 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4247. Min Range: -7.4247
Max Act: 6.9560. Min Act: -0.1666
Data Index: 4198556 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4247. Min Range: -7.4247
Max Act: 6.9872. Min Act: -0.1700
Data Index: 3443353 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4247. Min Range: -7.4247
Max Act: 6.9560. Min Act: -0.1700
Data Index: 841077 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4247. Min Range: -7.4247
Max Act: 6.9560. Min Act: -0.1700
Data Index: 667082 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #19