Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3749 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9765. Min Range: -7.9765
Max Act: 7.9765. Min Act: -0.1700
Data Index: 7168353 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9765. Min Range: -7.9765
Max Act: 7.7890. Min Act: -0.1700
Data Index: 3772431 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9765. Min Range: -7.9765
Max Act: 7.6015. Min Act: -0.1700
Data Index: 1734058 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9765. Min Range: -7.9765
Max Act: 7.5078. Min Act: -0.1700
Data Index: 126492 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9765. Min Range: -7.9765
Max Act: 7.5078. Min Act: -0.1700
Data Index: 6296180 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9765. Min Range: -7.9765
Max Act: 7.4140. Min Act: -0.1700
Data Index: 5222872 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9765. Min Range: -7.9765
Max Act: 7.4140. Min Act: -0.1700
Data Index: 5915628 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9765. Min Range: -7.9765
Max Act: 7.3828. Min Act: -0.1700
Data Index: 2087955 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9765. Min Range: -7.9765
Max Act: 7.3515. Min Act: -0.1700
Data Index: 7907538 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9765. Min Range: -7.9765
Max Act: 7.3203. Min Act: -0.1700
Data Index: 5939992 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9765. Min Range: -7.9765
Max Act: 7.3515. Min Act: -0.1700
Data Index: 2950902 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9765. Min Range: -7.9765
Max Act: 7.3515. Min Act: -0.1700
Data Index: 5278743 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9765. Min Range: -7.9765
Max Act: 7.3203. Min Act: -0.1700
Data Index: 6864094 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9765. Min Range: -7.9765
Max Act: 7.3203. Min Act: -0.1700
Data Index: 1306424 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9765. Min Range: -7.9765
Max Act: 7.2578. Min Act: -0.1700
Data Index: 7865322 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9765. Min Range: -7.9765
Max Act: 7.2578. Min Act: -0.1700
Data Index: 350396 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9765. Min Range: -7.9765
Max Act: 7.2578. Min Act: -0.1700
Data Index: 6234654 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9765. Min Range: -7.9765
Max Act: 7.2265. Min Act: -0.1700
Data Index: 447933 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9765. Min Range: -7.9765
Max Act: 7.2265. Min Act: -0.1700
Data Index: 7013869 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9765. Min Range: -7.9765
Max Act: 7.2265. Min Act: -0.1700
Data Index: 432377 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19