Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1320 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6716. Min Range: -8.6716
Max Act: 8.6716. Min Act: -0.1700
Data Index: 5491292 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6716. Min Range: -8.6716
Max Act: 8.4216. Min Act: -0.1700
Data Index: 8221885 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6716. Min Range: -8.6716
Max Act: 8.1091. Min Act: -0.1700
Data Index: 6704577 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6716. Min Range: -8.6716
Max Act: 8.0466. Min Act: -0.1700
Data Index: 417526 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6716. Min Range: -8.6716
Max Act: 7.8591. Min Act: -0.1700
Data Index: 7738501 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6716. Min Range: -8.6716
Max Act: 7.7966. Min Act: -0.1700
Data Index: 8363528 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6716. Min Range: -8.6716
Max Act: 7.8591. Min Act: -0.1700
Data Index: 5835959 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6716. Min Range: -8.6716
Max Act: 7.7966. Min Act: -0.1700
Data Index: 7566541 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6716. Min Range: -8.6716
Max Act: 7.7966. Min Act: -0.1700
Data Index: 6232133 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6716. Min Range: -8.6716
Max Act: 7.7341. Min Act: -0.1700
Data Index: 2304763 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6716. Min Range: -8.6716
Max Act: 7.7341. Min Act: -0.1700
Data Index: 2315322 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6716. Min Range: -8.6716
Max Act: 7.6716. Min Act: -0.1700
Data Index: 3256556 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6716. Min Range: -8.6716
Max Act: 7.5466. Min Act: -0.1700
Data Index: 1195725 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6716. Min Range: -8.6716
Max Act: 7.6091. Min Act: -0.1700
Data Index: 8604840 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6716. Min Range: -8.6716
Max Act: 7.6091. Min Act: -0.1700
Data Index: 615589 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6716. Min Range: -8.6716
Max Act: 7.6091. Min Act: -0.1700
Data Index: 987464 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6716. Min Range: -8.6716
Max Act: 7.5466. Min Act: -0.1700
Data Index: 4588143 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6716. Min Range: -8.6716
Max Act: 7.4841. Min Act: -0.1700
Data Index: 3582693 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6716. Min Range: -8.6716
Max Act: 7.5466. Min Act: -0.1700
Data Index: 4243146 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6716. Min Range: -8.6716
Max Act: 7.4841. Min Act: -0.1700
Data Index: 5901795 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #19