Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3547 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8593. Min Range: -8.8593
Max Act: 8.8593. Min Act: -0.1700
Data Index: 4534452 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8593. Min Range: -8.8593
Max Act: 8.4843. Min Act: -0.1700
Data Index: 4923657 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8593. Min Range: -8.8593
Max Act: 8.5468. Min Act: -0.1700
Data Index: 3071868 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8593. Min Range: -8.8593
Max Act: 8.4218. Min Act: -0.1700
Data Index: 5063693 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8593. Min Range: -8.8593
Max Act: 8.2343. Min Act: -0.1700
Data Index: 5510497 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8593. Min Range: -8.8593
Max Act: 8.0780. Min Act: -0.1700
Data Index: 2968501 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8593. Min Range: -8.8593
Max Act: 8.0155. Min Act: -0.1700
Data Index: 1235142 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8593. Min Range: -8.8593
Max Act: 7.9843. Min Act: -0.1700
Data Index: 7586569 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8593. Min Range: -8.8593
Max Act: 7.9218. Min Act: -0.1700
Data Index: 6979648 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8593. Min Range: -8.8593
Max Act: 7.8593. Min Act: -0.1700
Data Index: 4057392 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8593. Min Range: -8.8593
Max Act: 7.8905. Min Act: -0.1700
Data Index: 1786904 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8593. Min Range: -8.8593
Max Act: 7.7968. Min Act: -0.1700
Data Index: 559767 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8593. Min Range: -8.8593
Max Act: 7.7655. Min Act: -0.1700
Data Index: 1104556 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8593. Min Range: -8.8593
Max Act: 7.7655. Min Act: -0.1700
Data Index: 5313720 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8593. Min Range: -8.8593
Max Act: 7.7655. Min Act: -0.1700
Data Index: 176474 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8593. Min Range: -8.8593
Max Act: 7.7343. Min Act: -0.1700
Data Index: 1507601 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8593. Min Range: -8.8593
Max Act: 7.7343. Min Act: -0.1700
Data Index: 4090399 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8593. Min Range: -8.8593
Max Act: 7.6718. Min Act: -0.1700
Data Index: 5039179 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8593. Min Range: -8.8593
Max Act: 7.6405. Min Act: -0.1700
Data Index: 4481786 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8593. Min Range: -8.8593
Max Act: 7.6405. Min Act: -0.1700
Data Index: 1633537 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19