Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3125 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0509. Min Range: -7.0509
Max Act: 7.0509. Min Act: -0.1700
Data Index: 2959519 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0509. Min Range: -7.0509
Max Act: 6.9884. Min Act: -0.1700
Data Index: 6902489 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0509. Min Range: -7.0509
Max Act: 6.8634. Min Act: -0.1700
Data Index: 5374243 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0509. Min Range: -7.0509
Max Act: 6.8321. Min Act: -0.1700
Data Index: 6057313 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0509. Min Range: -7.0509
Max Act: 6.8009. Min Act: -0.1700
Data Index: 1944941 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0509. Min Range: -7.0509
Max Act: 6.7696. Min Act: -0.1700
Data Index: 6267506 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0509. Min Range: -7.0509
Max Act: 6.7384. Min Act: -0.1700
Data Index: 2770681 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0509. Min Range: -7.0509
Max Act: 6.7071. Min Act: -0.1700
Data Index: 891482 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0509. Min Range: -7.0509
Max Act: 6.7071. Min Act: -0.1700
Data Index: 5687912 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0509. Min Range: -7.0509
Max Act: 6.7071. Min Act: -0.1700
Data Index: 35329 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0509. Min Range: -7.0509
Max Act: 6.6759. Min Act: -0.1700
Data Index: 7865732 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0509. Min Range: -7.0509
Max Act: 6.6759. Min Act: -0.1700
Data Index: 295942 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0509. Min Range: -7.0509
Max Act: 6.7071. Min Act: -0.1700
Data Index: 48410 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0509. Min Range: -7.0509
Max Act: 6.6759. Min Act: -0.1700
Data Index: 593258 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0509. Min Range: -7.0509
Max Act: 6.6759. Min Act: -0.1700
Data Index: 1375190 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0509. Min Range: -7.0509
Max Act: 6.6134. Min Act: -0.1700
Data Index: 5878180 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0509. Min Range: -7.0509
Max Act: 6.6134. Min Act: -0.1700
Data Index: 763336 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0509. Min Range: -7.0509
Max Act: 6.6446. Min Act: -0.1700
Data Index: 891481 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0509. Min Range: -7.0509
Max Act: 6.5821. Min Act: -0.1700
Data Index: 1646622 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0509. Min Range: -7.0509
Max Act: 6.5821. Min Act: -0.1700
Data Index: 2203815 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19