Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 266 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6535. Min Range: -6.6535
Max Act: 6.6535. Min Act: -0.1700
Data Index: 813372 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6535. Min Range: -6.6535
Max Act: 6.4347. Min Act: -0.1700
Data Index: 6535211 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6535. Min Range: -6.6535
Max Act: 6.4347. Min Act: -0.1700
Data Index: 2326155 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6535. Min Range: -6.6535
Max Act: 6.3410. Min Act: -0.1700
Data Index: 5001455 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6535. Min Range: -6.6535
Max Act: 6.3097. Min Act: -0.1700
Data Index: 1202247 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6535. Min Range: -6.6535
Max Act: 6.0910. Min Act: -0.1700
Data Index: 6202891 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6535. Min Range: -6.6535
Max Act: 6.0597. Min Act: -0.1700
Data Index: 2356519 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6535. Min Range: -6.6535
Max Act: 6.0285. Min Act: -0.1700
Data Index: 6161289 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6535. Min Range: -6.6535
Max Act: 5.9972. Min Act: -0.1700
Data Index: 6619967 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6535. Min Range: -6.6535
Max Act: 5.8722. Min Act: -0.1700
Data Index: 6161294 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6535. Min Range: -6.6535
Max Act: 5.8410. Min Act: -0.1700
Data Index: 8499268 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6535. Min Range: -6.6535
Max Act: 5.8410. Min Act: -0.1700
Data Index: 8030847 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6535. Min Range: -6.6535
Max Act: 5.8410. Min Act: -0.1700
Data Index: 525375 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6535. Min Range: -6.6535
Max Act: 5.7160. Min Act: -0.1700
Data Index: 4109195 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6535. Min Range: -6.6535
Max Act: 5.7160. Min Act: -0.1700
Data Index: 4493604 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6535. Min Range: -6.6535
Max Act: 5.7160. Min Act: -0.1700
Data Index: 182718 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6535. Min Range: -6.6535
Max Act: 5.6535. Min Act: -0.1700
Data Index: 1680340 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6535. Min Range: -6.6535
Max Act: 5.6535. Min Act: -0.1700
Data Index: 3579896 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6535. Min Range: -6.6535
Max Act: 5.5597. Min Act: -0.1700
Data Index: 2606934 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6535. Min Range: -6.6535
Max Act: 5.5597. Min Act: -0.1700
Data Index: 7296634 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19