Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3209 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3807. Min Range: -6.3807
Max Act: 6.3807. Min Act: -0.1700
Data Index: 4957201 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3807. Min Range: -6.3807
Max Act: 6.2245. Min Act: -0.1700
Data Index: 7110192 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3807. Min Range: -6.3807
Max Act: 6.0995. Min Act: -0.1700
Data Index: 5787286 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3807. Min Range: -6.3807
Max Act: 6.0995. Min Act: -0.1700
Data Index: 7966147 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3807. Min Range: -6.3807
Max Act: 6.0995. Min Act: -0.1700
Data Index: 2634527 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3807. Min Range: -6.3807
Max Act: 6.0057. Min Act: -0.1700
Data Index: 7590357 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3807. Min Range: -6.3807
Max Act: 6.0057. Min Act: -0.1700
Data Index: 301976 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3807. Min Range: -6.3807
Max Act: 5.9745. Min Act: -0.1700
Data Index: 2510827 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3807. Min Range: -6.3807
Max Act: 5.9745. Min Act: -0.1700
Data Index: 2444177 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3807. Min Range: -6.3807
Max Act: 5.9745. Min Act: -0.1700
Data Index: 4254940 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3807. Min Range: -6.3807
Max Act: 5.9432. Min Act: -0.1700
Data Index: 2653524 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3807. Min Range: -6.3807
Max Act: 5.9745. Min Act: -0.1700
Data Index: 8072708 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3807. Min Range: -6.3807
Max Act: 5.8807. Min Act: -0.1700
Data Index: 5550916 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3807. Min Range: -6.3807
Max Act: 5.8807. Min Act: -0.1700
Data Index: 4515913 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3807. Min Range: -6.3807
Max Act: 5.8807. Min Act: -0.1700
Data Index: 1781257 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3807. Min Range: -6.3807
Max Act: 5.8807. Min Act: -0.1700
Data Index: 4910891 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3807. Min Range: -6.3807
Max Act: 5.8807. Min Act: -0.1700
Data Index: 6917553 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3807. Min Range: -6.3807
Max Act: 5.8495. Min Act: -0.1700
Data Index: 3762919 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3807. Min Range: -6.3807
Max Act: 5.8807. Min Act: -0.1700
Data Index: 3659753 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3807. Min Range: -6.3807
Max Act: 5.8495. Min Act: -0.1700
Data Index: 5198789 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19