Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1285 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2722. Min Range: -8.2722
Max Act: 8.2722. Min Act: -0.1700
Data Index: 6447032 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2722. Min Range: -8.2722
Max Act: 8.2409. Min Act: -0.1700
Data Index: 57677 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2722. Min Range: -8.2722
Max Act: 8.2097. Min Act: -0.1700
Data Index: 3651436 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2722. Min Range: -8.2722
Max Act: 8.1784. Min Act: -0.1700
Data Index: 916301 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2722. Min Range: -8.2722
Max Act: 8.1472. Min Act: -0.1700
Data Index: 8450809 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2722. Min Range: -8.2722
Max Act: 8.0534. Min Act: -0.1700
Data Index: 897317 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2722. Min Range: -8.2722
Max Act: 7.9284. Min Act: -0.1700
Data Index: 768336 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2722. Min Range: -8.2722
Max Act: 7.8347. Min Act: -0.1700
Data Index: 7189425 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2722. Min Range: -8.2722
Max Act: 7.8034. Min Act: -0.1700
Data Index: 8562580 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2722. Min Range: -8.2722
Max Act: 7.8347. Min Act: -0.1700
Data Index: 6483950 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2722. Min Range: -8.2722
Max Act: 7.8347. Min Act: -0.1700
Data Index: 4767059 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2722. Min Range: -8.2722
Max Act: 7.8034. Min Act: -0.1700
Data Index: 6059116 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2722. Min Range: -8.2722
Max Act: 7.8034. Min Act: -0.1700
Data Index: 1483166 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2722. Min Range: -8.2722
Max Act: 7.7722. Min Act: -0.1700
Data Index: 4521155 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2722. Min Range: -8.2722
Max Act: 7.7722. Min Act: -0.1700
Data Index: 6084250 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2722. Min Range: -8.2722
Max Act: 7.7097. Min Act: -0.1700
Data Index: 8698177 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2722. Min Range: -8.2722
Max Act: 7.7097. Min Act: -0.1700
Data Index: 1170707 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2722. Min Range: -8.2722
Max Act: 7.6472. Min Act: -0.1700
Data Index: 6766026 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2722. Min Range: -8.2722
Max Act: 7.6472. Min Act: -0.1700
Data Index: 4828343 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2722. Min Range: -8.2722
Max Act: 7.6159. Min Act: -0.1700
Data Index: 8056957 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19