Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2849 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6592. Min Range: -7.6592
Max Act: 7.6592. Min Act: -0.1700
Data Index: 317579 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6592. Min Range: -7.6592
Max Act: 7.5655. Min Act: -0.1700
Data Index: 4397899 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6592. Min Range: -7.6592
Max Act: 7.5342. Min Act: -0.1700
Data Index: 1842 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6592. Min Range: -7.6592
Max Act: 7.4717. Min Act: -0.1700
Data Index: 4743485 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6592. Min Range: -7.6592
Max Act: 7.4717. Min Act: -0.1700
Data Index: 4088234 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6592. Min Range: -7.6592
Max Act: 7.4717. Min Act: -0.1700
Data Index: 5290362 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6592. Min Range: -7.6592
Max Act: 7.4405. Min Act: -0.1700
Data Index: 2637320 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6592. Min Range: -7.6592
Max Act: 7.4717. Min Act: -0.1700
Data Index: 8310107 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6592. Min Range: -7.6592
Max Act: 7.3780. Min Act: -0.1700
Data Index: 2305714 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6592. Min Range: -7.6592
Max Act: 7.3780. Min Act: -0.1700
Data Index: 3736768 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6592. Min Range: -7.6592
Max Act: 7.3780. Min Act: -0.1700
Data Index: 2042529 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6592. Min Range: -7.6592
Max Act: 7.3467. Min Act: -0.1700
Data Index: 6177573 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6592. Min Range: -7.6592
Max Act: 7.3467. Min Act: -0.1700
Data Index: 3266493 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6592. Min Range: -7.6592
Max Act: 7.3467. Min Act: -0.1700
Data Index: 8297103 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6592. Min Range: -7.6592
Max Act: 7.3467. Min Act: -0.1700
Data Index: 2817594 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6592. Min Range: -7.6592
Max Act: 7.3155. Min Act: -0.1700
Data Index: 4260566 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6592. Min Range: -7.6592
Max Act: 7.3155. Min Act: -0.1700
Data Index: 4049102 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6592. Min Range: -7.6592
Max Act: 7.2842. Min Act: -0.1700
Data Index: 8493900 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6592. Min Range: -7.6592
Max Act: 7.2842. Min Act: -0.1700
Data Index: 4900598 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6592. Min Range: -7.6592
Max Act: 7.2530. Min Act: -0.1700
Data Index: 2501564 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19