Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2847 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.0017. Min Range: -1.0017
Max Act: 1.0017. Min Act: -0.1700
Data Index: 399933 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0017. Min Range: -1.0017
Max Act: 0.9930. Min Act: -0.1700
Data Index: 6383619 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0017. Min Range: -1.0017
Max Act: 0.9930. Min Act: -0.1700
Data Index: 5631306 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0017. Min Range: -1.0017
Max Act: 0.9670. Min Act: -0.1700
Data Index: 4034685 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0017. Min Range: -1.0017
Max Act: 0.9584. Min Act: -0.1700
Data Index: 7595544 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0017. Min Range: -1.0017
Max Act: 0.9584. Min Act: -0.1700
Data Index: 7629236 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0017. Min Range: -1.0017
Max Act: 0.9584. Min Act: -0.1700
Data Index: 8275192 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0017. Min Range: -1.0017
Max Act: 0.9584. Min Act: -0.1700
Data Index: 2754400 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0017. Min Range: -1.0017
Max Act: 0.9411. Min Act: -0.1700
Data Index: 5040359 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0017. Min Range: -1.0017
Max Act: 0.9411. Min Act: -0.1700
Data Index: 1298133 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0017. Min Range: -1.0017
Max Act: 0.9239. Min Act: -0.1700
Data Index: 6460641 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0017. Min Range: -1.0017
Max Act: 0.9325. Min Act: -0.1700
Data Index: 5129964 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0017. Min Range: -1.0017
Max Act: 0.9239. Min Act: -0.1700
Data Index: 5752556 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0017. Min Range: -1.0017
Max Act: 0.9239. Min Act: -0.1700
Data Index: 6588250 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0017. Min Range: -1.0017
Max Act: 0.8982. Min Act: -0.1700
Data Index: 6899801 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0017. Min Range: -1.0017
Max Act: 0.9068. Min Act: -0.1700
Data Index: 7968596 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0017. Min Range: -1.0017
Max Act: 0.8897. Min Act: -0.1700
Data Index: 5147185 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0017. Min Range: -1.0017
Max Act: 0.8811. Min Act: -0.1700
Data Index: 7586847 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0017. Min Range: -1.0017
Max Act: 0.8897. Min Act: -0.1700
Data Index: 30236 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0017. Min Range: -1.0017
Max Act: 0.8726. Min Act: -0.1700
Data Index: 5646505 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19