Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2277 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4998. Min Range: -8.4998
Max Act: 8.4998. Min Act: -0.1700
Data Index: 5230103 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4998. Min Range: -8.4998
Max Act: 8.4998. Min Act: -0.1700
Data Index: 856883 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4998. Min Range: -8.4998
Max Act: 8.3748. Min Act: -0.1700
Data Index: 3785326 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4998. Min Range: -8.4998
Max Act: 8.1873. Min Act: -0.1700
Data Index: 4289023 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4998. Min Range: -8.4998
Max Act: 8.1560. Min Act: -0.1700
Data Index: 8112843 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4998. Min Range: -8.4998
Max Act: 8.0935. Min Act: -0.1700
Data Index: 1225417 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4998. Min Range: -8.4998
Max Act: 8.0935. Min Act: -0.1700
Data Index: 280098 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4998. Min Range: -8.4998
Max Act: 8.0623. Min Act: -0.1700
Data Index: 6929690 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4998. Min Range: -8.4998
Max Act: 8.0935. Min Act: -0.1700
Data Index: 398530 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4998. Min Range: -8.4998
Max Act: 8.0310. Min Act: -0.1700
Data Index: 4663240 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4998. Min Range: -8.4998
Max Act: 7.9998. Min Act: -0.1700
Data Index: 1003607 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4998. Min Range: -8.4998
Max Act: 7.9998. Min Act: -0.1700
Data Index: 8143874 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4998. Min Range: -8.4998
Max Act: 7.9685. Min Act: -0.1700
Data Index: 8679163 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4998. Min Range: -8.4998
Max Act: 7.9998. Min Act: -0.1700
Data Index: 7830045 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4998. Min Range: -8.4998
Max Act: 7.9373. Min Act: -0.1700
Data Index: 7064301 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4998. Min Range: -8.4998
Max Act: 7.9685. Min Act: -0.1700
Data Index: 7617374 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4998. Min Range: -8.4998
Max Act: 7.9373. Min Act: -0.1700
Data Index: 6565980 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4998. Min Range: -8.4998
Max Act: 7.8748. Min Act: -0.1700
Data Index: 5611737 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4998. Min Range: -8.4998
Max Act: 7.9373. Min Act: -0.1700
Data Index: 5003499 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4998. Min Range: -8.4998
Max Act: 7.8748. Min Act: -0.1700
Data Index: 3842144 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #19