Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5417. Min Range: -7.5417
Max Act: 7.5417. Min Act: -0.1700
Data Index: 8471943 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5417. Min Range: -7.5417
Max Act: 7.3230. Min Act: -0.1700
Data Index: 2957848 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5417. Min Range: -7.5417
Max Act: 7.3230. Min Act: -0.1700
Data Index: 2679893 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5417. Min Range: -7.5417
Max Act: 7.2917. Min Act: -0.1700
Data Index: 7739434 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5417. Min Range: -7.5417
Max Act: 7.2605. Min Act: -0.1700
Data Index: 6598457 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5417. Min Range: -7.5417
Max Act: 7.2917. Min Act: -0.1700
Data Index: 2844451 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5417. Min Range: -7.5417
Max Act: 7.1980. Min Act: -0.1700
Data Index: 6189730 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5417. Min Range: -7.5417
Max Act: 7.1980. Min Act: -0.1700
Data Index: 2154462 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5417. Min Range: -7.5417
Max Act: 7.1980. Min Act: -0.1700
Data Index: 3544842 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5417. Min Range: -7.5417
Max Act: 7.1355. Min Act: -0.1700
Data Index: 8558560 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5417. Min Range: -7.5417
Max Act: 7.1042. Min Act: -0.1700
Data Index: 6151220 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5417. Min Range: -7.5417
Max Act: 7.0417. Min Act: -0.1700
Data Index: 5906565 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5417. Min Range: -7.5417
Max Act: 7.0417. Min Act: -0.1700
Data Index: 6443803 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5417. Min Range: -7.5417
Max Act: 7.0417. Min Act: -0.1700
Data Index: 2342736 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5417. Min Range: -7.5417
Max Act: 7.0417. Min Act: -0.1700
Data Index: 4276483 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5417. Min Range: -7.5417
Max Act: 7.0105. Min Act: -0.1700
Data Index: 6735837 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5417. Min Range: -7.5417
Max Act: 6.9792. Min Act: -0.1700
Data Index: 3544843 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5417. Min Range: -7.5417
Max Act: 6.9792. Min Act: -0.1700
Data Index: 7519807 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5417. Min Range: -7.5417
Max Act: 6.9792. Min Act: -0.1700
Data Index: 3121162 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5417. Min Range: -7.5417
Max Act: 6.9792. Min Act: -0.1700
Data Index: 7559845 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #19