Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2534 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3793. Min Range: -5.3793
Max Act: 5.3793. Min Act: -0.1700
Data Index: 6272821 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3793. Min Range: -5.3793
Max Act: 5.0043. Min Act: -0.1700
Data Index: 1471842 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3793. Min Range: -5.3793
Max Act: 4.9418. Min Act: -0.1700
Data Index: 7898888 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3793. Min Range: -5.3793
Max Act: 4.9418. Min Act: -0.1700
Data Index: 5310545 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3793. Min Range: -5.3793
Max Act: 4.9418. Min Act: -0.1700
Data Index: 3441383 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3793. Min Range: -5.3793
Max Act: 4.8793. Min Act: -0.1700
Data Index: 1633441 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3793. Min Range: -5.3793
Max Act: 4.8793. Min Act: -0.1700
Data Index: 7898883 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3793. Min Range: -5.3793
Max Act: 4.9105. Min Act: -0.1700
Data Index: 43538 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3793. Min Range: -5.3793
Max Act: 4.8793. Min Act: -0.1700
Data Index: 2811065 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3793. Min Range: -5.3793
Max Act: 4.8480. Min Act: -0.1700
Data Index: 4952136 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3793. Min Range: -5.3793
Max Act: 4.8480. Min Act: -0.1700
Data Index: 7642542 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3793. Min Range: -5.3793
Max Act: 4.8793. Min Act: -0.1700
Data Index: 3558520 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3793. Min Range: -5.3793
Max Act: 4.8168. Min Act: -0.1700
Data Index: 3111065 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3793. Min Range: -5.3793
Max Act: 4.8168. Min Act: -0.1700
Data Index: 8449797 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3793. Min Range: -5.3793
Max Act: 4.8168. Min Act: -0.1700
Data Index: 8447800 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3793. Min Range: -5.3793
Max Act: 4.7855. Min Act: -0.1700
Data Index: 1808850 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3793. Min Range: -5.3793
Max Act: 4.7543. Min Act: -0.1700
Data Index: 376599 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3793. Min Range: -5.3793
Max Act: 4.7543. Min Act: -0.1700
Data Index: 6697795 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3793. Min Range: -5.3793
Max Act: 4.7543. Min Act: -0.1700
Data Index: 2494521 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3793. Min Range: -5.3793
Max Act: 4.7543. Min Act: -0.1700
Data Index: 848404 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19