Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4349 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7460. Min Range: -5.7460
Max Act: 5.7460. Min Act: -0.1700
Data Index: 279279 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7460. Min Range: -5.7460
Max Act: 5.6522. Min Act: -0.1700
Data Index: 3957485 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7460. Min Range: -5.7460
Max Act: 5.6522. Min Act: -0.1700
Data Index: 2627854 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7460. Min Range: -5.7460
Max Act: 5.5897. Min Act: -0.1700
Data Index: 4065660 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7460. Min Range: -5.7460
Max Act: 5.5585. Min Act: -0.1700
Data Index: 4322935 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7460. Min Range: -5.7460
Max Act: 5.5272. Min Act: -0.1700
Data Index: 7448535 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7460. Min Range: -5.7460
Max Act: 5.5272. Min Act: -0.1700
Data Index: 8667472 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7460. Min Range: -5.7460
Max Act: 5.4960. Min Act: -0.1700
Data Index: 3879220 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7460. Min Range: -5.7460
Max Act: 5.4960. Min Act: -0.1700
Data Index: 3957489 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7460. Min Range: -5.7460
Max Act: 5.4960. Min Act: -0.1699
Data Index: 8083467 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7460. Min Range: -5.7460
Max Act: 5.4960. Min Act: -0.1700
Data Index: 8338034 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7460. Min Range: -5.7460
Max Act: 5.4960. Min Act: -0.1700
Data Index: 1863903 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7460. Min Range: -5.7460
Max Act: 5.4960. Min Act: -0.1700
Data Index: 7448536 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7460. Min Range: -5.7460
Max Act: 5.4647. Min Act: -0.1700
Data Index: 4656584 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7460. Min Range: -5.7460
Max Act: 5.4335. Min Act: -0.1700
Data Index: 3862826 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7460. Min Range: -5.7460
Max Act: 5.4335. Min Act: -0.1700
Data Index: 279288 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7460. Min Range: -5.7460
Max Act: 5.4335. Min Act: -0.1700
Data Index: 1863906 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7460. Min Range: -5.7460
Max Act: 5.4335. Min Act: -0.1700
Data Index: 8654680 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7460. Min Range: -5.7460
Max Act: 5.4022. Min Act: -0.1700
Data Index: 4656589 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7460. Min Range: -5.7460
Max Act: 5.3710. Min Act: -0.1700
Data Index: 3957486 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19