Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3613 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0537. Min Range: -9.0537
Max Act: 9.0537. Min Act: -0.1699
Data Index: 6303978 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0537. Min Range: -9.0537
Max Act: 9.0537. Min Act: -0.1700
Data Index: 5578053 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0537. Min Range: -9.0537
Max Act: 8.9287. Min Act: -0.1700
Data Index: 4280741 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0537. Min Range: -9.0537
Max Act: 8.7412. Min Act: -0.1700
Data Index: 2289284 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0537. Min Range: -9.0537
Max Act: 8.4912. Min Act: -0.1700
Data Index: 674287 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0537. Min Range: -9.0537
Max Act: 8.4912. Min Act: -0.1700
Data Index: 6352756 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0537. Min Range: -9.0537
Max Act: 8.4287. Min Act: -0.1700
Data Index: 1133422 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0537. Min Range: -9.0537
Max Act: 8.3662. Min Act: -0.1700
Data Index: 543044 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0537. Min Range: -9.0537
Max Act: 8.3662. Min Act: -0.1700
Data Index: 6303975 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0537. Min Range: -9.0537
Max Act: 8.3662. Min Act: -0.1700
Data Index: 4825922 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0537. Min Range: -9.0537
Max Act: 8.3037. Min Act: -0.1700
Data Index: 8591903 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0537. Min Range: -9.0537
Max Act: 8.3037. Min Act: -0.1700
Data Index: 8488616 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0537. Min Range: -9.0537
Max Act: 8.1787. Min Act: -0.1700
Data Index: 2821890 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0537. Min Range: -9.0537
Max Act: 8.1787. Min Act: -0.1700
Data Index: 5377512 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0537. Min Range: -9.0537
Max Act: 8.1787. Min Act: -0.1700
Data Index: 2800504 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0537. Min Range: -9.0537
Max Act: 8.1162. Min Act: -0.1700
Data Index: 5549583 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0537. Min Range: -9.0537
Max Act: 8.0850. Min Act: -0.1700
Data Index: 4825924 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0537. Min Range: -9.0537
Max Act: 8.0850. Min Act: -0.1700
Data Index: 2428371 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0537. Min Range: -9.0537
Max Act: 8.0850. Min Act: -0.1700
Data Index: 2058888 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0537. Min Range: -9.0537
Max Act: 8.0537. Min Act: -0.1700
Data Index: 2449101 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19