Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1915 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1849. Min Range: -7.1849
Max Act: 7.1849. Min Act: -0.1700
Data Index: 7224415 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1849. Min Range: -7.1849
Max Act: 6.9349. Min Act: -0.1700
Data Index: 2981407 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1849. Min Range: -7.1849
Max Act: 6.9349. Min Act: -0.1700
Data Index: 5791422 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1849. Min Range: -7.1849
Max Act: 6.9037. Min Act: -0.1700
Data Index: 4041361 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1849. Min Range: -7.1849
Max Act: 6.8724. Min Act: -0.1700
Data Index: 594543 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1849. Min Range: -7.1849
Max Act: 6.9037. Min Act: -0.1700
Data Index: 7153114 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1849. Min Range: -7.1849
Max Act: 6.8412. Min Act: -0.1700
Data Index: 3356900 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1849. Min Range: -7.1849
Max Act: 6.8724. Min Act: -0.1700
Data Index: 7286128 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1849. Min Range: -7.1849
Max Act: 6.8099. Min Act: -0.1700
Data Index: 8623335 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1849. Min Range: -7.1849
Max Act: 6.8099. Min Act: -0.1700
Data Index: 7876215 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1849. Min Range: -7.1849
Max Act: 6.7787. Min Act: -0.1700
Data Index: 2563025 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1849. Min Range: -7.1849
Max Act: 6.7474. Min Act: -0.1700
Data Index: 6569603 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1849. Min Range: -7.1849
Max Act: 6.7474. Min Act: -0.1700
Data Index: 8292056 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1849. Min Range: -7.1849
Max Act: 6.7162. Min Act: -0.1700
Data Index: 3945117 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1849. Min Range: -7.1849
Max Act: 6.7162. Min Act: -0.1700
Data Index: 3948972 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1849. Min Range: -7.1849
Max Act: 6.6849. Min Act: -0.1700
Data Index: 5945782 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1849. Min Range: -7.1849
Max Act: 6.7162. Min Act: -0.1700
Data Index: 4248509 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1849. Min Range: -7.1849
Max Act: 6.6537. Min Act: -0.1700
Data Index: 6901142 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1849. Min Range: -7.1849
Max Act: 6.6849. Min Act: -0.1700
Data Index: 5041820 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1849. Min Range: -7.1849
Max Act: 6.6849. Min Act: -0.1700
Data Index: 2099163 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19