Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 494 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1432. Min Range: -6.1432
Max Act: 6.1432. Min Act: -0.1700
Data Index: 7326647 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1432. Min Range: -6.1432
Max Act: 6.0807. Min Act: -0.1700
Data Index: 6861342 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1432. Min Range: -6.1432
Max Act: 5.8620. Min Act: -0.1700
Data Index: 8400115 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1432. Min Range: -6.1432
Max Act: 5.8307. Min Act: -0.1700
Data Index: 5579180 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1432. Min Range: -6.1432
Max Act: 5.8307. Min Act: -0.1700
Data Index: 7551016 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1432. Min Range: -6.1432
Max Act: 5.7682. Min Act: -0.1700
Data Index: 2816414 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1432. Min Range: -6.1432
Max Act: 5.7995. Min Act: -0.1700
Data Index: 1829502 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1432. Min Range: -6.1432
Max Act: 5.7995. Min Act: -0.1700
Data Index: 6628394 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1432. Min Range: -6.1432
Max Act: 5.7682. Min Act: -0.1700
Data Index: 2129096 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1432. Min Range: -6.1432
Max Act: 5.7682. Min Act: -0.1700
Data Index: 5399782 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1432. Min Range: -6.1432
Max Act: 5.7370. Min Act: -0.1700
Data Index: 2956047 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1432. Min Range: -6.1432
Max Act: 5.7370. Min Act: -0.1700
Data Index: 2439170 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1432. Min Range: -6.1432
Max Act: 5.7057. Min Act: -0.1700
Data Index: 3525647 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1432. Min Range: -6.1432
Max Act: 5.7057. Min Act: -0.1700
Data Index: 2173990 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1432. Min Range: -6.1432
Max Act: 5.6745. Min Act: -0.1700
Data Index: 1866333 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1432. Min Range: -6.1432
Max Act: 5.6745. Min Act: -0.1700
Data Index: 2616167 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1432. Min Range: -6.1432
Max Act: 5.6120. Min Act: -0.1700
Data Index: 3201873 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1432. Min Range: -6.1432
Max Act: 5.6432. Min Act: -0.1700
Data Index: 7841189 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1432. Min Range: -6.1432
Max Act: 5.6432. Min Act: -0.1700
Data Index: 4370788 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1432. Min Range: -6.1432
Max Act: 5.6120. Min Act: -0.1700
Data Index: 5955989 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19