Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 829 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6923. Min Range: -6.6923
Max Act: 6.6923. Min Act: -0.1700
Data Index: 1396569 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6923. Min Range: -6.6923
Max Act: 6.4423. Min Act: -0.1700
Data Index: 3313714 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6923. Min Range: -6.6923
Max Act: 6.4423. Min Act: -0.1700
Data Index: 2986664 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6923. Min Range: -6.6923
Max Act: 6.4423. Min Act: -0.1700
Data Index: 608134 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6923. Min Range: -6.6923
Max Act: 6.4423. Min Act: -0.1700
Data Index: 8215397 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6923. Min Range: -6.6923
Max Act: 6.3798. Min Act: -0.1700
Data Index: 280065 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6923. Min Range: -6.6923
Max Act: 6.4110. Min Act: -0.1700
Data Index: 6403177 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6923. Min Range: -6.6923
Max Act: 6.3798. Min Act: -0.1700
Data Index: 992470 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6923. Min Range: -6.6923
Max Act: 6.3485. Min Act: -0.1700
Data Index: 2502038 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6923. Min Range: -6.6923
Max Act: 6.3173. Min Act: -0.1700
Data Index: 7289903 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6923. Min Range: -6.6923
Max Act: 6.2860. Min Act: -0.1700
Data Index: 1479848 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6923. Min Range: -6.6923
Max Act: 6.2860. Min Act: -0.1700
Data Index: 5846281 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6923. Min Range: -6.6923
Max Act: 6.2548. Min Act: -0.1700
Data Index: 4574468 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6923. Min Range: -6.6923
Max Act: 6.2548. Min Act: -0.1700
Data Index: 8738611 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6923. Min Range: -6.6923
Max Act: 6.2548. Min Act: -0.1700
Data Index: 5686064 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6923. Min Range: -6.6923
Max Act: 6.2235. Min Act: -0.1700
Data Index: 3178088 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6923. Min Range: -6.6923
Max Act: 6.1923. Min Act: -0.1700
Data Index: 7549580 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6923. Min Range: -6.6923
Max Act: 6.1923. Min Act: -0.1700
Data Index: 4065 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6923. Min Range: -6.6923
Max Act: 6.1923. Min Act: -0.1700
Data Index: 6002439 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6923. Min Range: -6.6923
Max Act: 6.2235. Min Act: -0.1700
Data Index: 6174595 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19