Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3263 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3438. Min Range: -6.3438
Max Act: 6.3438. Min Act: -0.1700
Data Index: 4421965 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3438. Min Range: -6.3438
Max Act: 6.3126. Min Act: -0.1700
Data Index: 1553917 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3438. Min Range: -6.3438
Max Act: 6.2188. Min Act: -0.1700
Data Index: 4004974 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3438. Min Range: -6.3438
Max Act: 6.1876. Min Act: -0.1700
Data Index: 7116935 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3438. Min Range: -6.3438
Max Act: 6.1251. Min Act: -0.1700
Data Index: 7623283 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3438. Min Range: -6.3438
Max Act: 6.1251. Min Act: -0.1700
Data Index: 7419353 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3438. Min Range: -6.3438
Max Act: 6.1251. Min Act: -0.1700
Data Index: 7762829 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3438. Min Range: -6.3438
Max Act: 6.0938. Min Act: -0.1699
Data Index: 397728 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3438. Min Range: -6.3438
Max Act: 6.0313. Min Act: -0.1700
Data Index: 296333 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3438. Min Range: -6.3438
Max Act: 6.0313. Min Act: -0.1700
Data Index: 2969664 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3438. Min Range: -6.3438
Max Act: 6.0001. Min Act: -0.1700
Data Index: 3359857 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3438. Min Range: -6.3438
Max Act: 6.0001. Min Act: -0.1700
Data Index: 7331096 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3438. Min Range: -6.3438
Max Act: 5.9688. Min Act: -0.1700
Data Index: 2857151 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3438. Min Range: -6.3438
Max Act: 5.9376. Min Act: -0.1700
Data Index: 4484064 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3438. Min Range: -6.3438
Max Act: 5.9688. Min Act: -0.1700
Data Index: 1185716 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3438. Min Range: -6.3438
Max Act: 6.0001. Min Act: -0.1700
Data Index: 6607191 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3438. Min Range: -6.3438
Max Act: 5.9688. Min Act: -0.1700
Data Index: 2607231 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3438. Min Range: -6.3438
Max Act: 5.9376. Min Act: -0.1700
Data Index: 5954619 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3438. Min Range: -6.3438
Max Act: 5.9376. Min Act: -0.1700
Data Index: 297208 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3438. Min Range: -6.3438
Max Act: 5.9063. Min Act: -0.1700
Data Index: 5561525 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #19