Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3441 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5258. Min Range: -6.5258
Max Act: 6.5258. Min Act: -0.1700
Data Index: 8423827 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5258. Min Range: -6.5258
Max Act: 6.3383. Min Act: -0.1700
Data Index: 2089713 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5258. Min Range: -6.5258
Max Act: 5.8383. Min Act: -0.1700
Data Index: 6330007 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5258. Min Range: -6.5258
Max Act: 5.8695. Min Act: -0.1700
Data Index: 756673 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5258. Min Range: -6.5258
Max Act: 5.8383. Min Act: -0.1700
Data Index: 2411033 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5258. Min Range: -6.5258
Max Act: 5.7758. Min Act: -0.1700
Data Index: 836093 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5258. Min Range: -6.5258
Max Act: 5.6820. Min Act: -0.1700
Data Index: 6201482 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5258. Min Range: -6.5258
Max Act: 5.6820. Min Act: -0.1700
Data Index: 7022354 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5258. Min Range: -6.5258
Max Act: 5.6820. Min Act: -0.1700
Data Index: 921659 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5258. Min Range: -6.5258
Max Act: 5.6820. Min Act: -0.1700
Data Index: 6330009 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5258. Min Range: -6.5258
Max Act: 5.6820. Min Act: -0.1700
Data Index: 6231827 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5258. Min Range: -6.5258
Max Act: 5.6820. Min Act: -0.1700
Data Index: 6330013 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5258. Min Range: -6.5258
Max Act: 5.6508. Min Act: -0.1700
Data Index: 7022349 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5258. Min Range: -6.5258
Max Act: 5.6508. Min Act: -0.1700
Data Index: 756678 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5258. Min Range: -6.5258
Max Act: 5.6195. Min Act: -0.1700
Data Index: 921664 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5258. Min Range: -6.5258
Max Act: 5.6195. Min Act: -0.1700
Data Index: 921653 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5258. Min Range: -6.5258
Max Act: 5.5570. Min Act: -0.1700
Data Index: 7022345 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5258. Min Range: -6.5258
Max Act: 5.5883. Min Act: -0.1700
Data Index: 6201486 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5258. Min Range: -6.5258
Max Act: 5.5883. Min Act: -0.1700
Data Index: 921665 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5258. Min Range: -6.5258
Max Act: 5.5570. Min Act: -0.1700
Data Index: 3685837 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19