Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3485 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4063. Min Range: -5.4063
Max Act: 5.4063. Min Act: -0.1700
Data Index: 5274220 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4063. Min Range: -5.4063
Max Act: 5.2501. Min Act: -0.1700
Data Index: 8018756 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4063. Min Range: -5.4063
Max Act: 5.1251. Min Act: -0.1700
Data Index: 4860402 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4063. Min Range: -5.4063
Max Act: 5.0626. Min Act: -0.1700
Data Index: 8018757 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4063. Min Range: -5.4063
Max Act: 5.0626. Min Act: -0.1700
Data Index: 5369650 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4063. Min Range: -5.4063
Max Act: 5.0626. Min Act: -0.1700
Data Index: 5475191 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4063. Min Range: -5.4063
Max Act: 5.0001. Min Act: -0.1700
Data Index: 3546748 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4063. Min Range: -5.4063
Max Act: 5.0001. Min Act: -0.1700
Data Index: 1346161 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4063. Min Range: -5.4063
Max Act: 5.0001. Min Act: -0.1700
Data Index: 423241 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4063. Min Range: -5.4063
Max Act: 5.0001. Min Act: -0.1700
Data Index: 134512 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4063. Min Range: -5.4063
Max Act: 4.9688. Min Act: -0.1700
Data Index: 8557033 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4063. Min Range: -5.4063
Max Act: 4.9063. Min Act: -0.1700
Data Index: 5208169 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4063. Min Range: -5.4063
Max Act: 4.9376. Min Act: -0.1700
Data Index: 5861659 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4063. Min Range: -5.4063
Max Act: 4.9376. Min Act: -0.1700
Data Index: 5475190 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4063. Min Range: -5.4063
Max Act: 4.9063. Min Act: -0.1700
Data Index: 8821533 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4063. Min Range: -5.4063
Max Act: 4.9063. Min Act: -0.1700
Data Index: 3357518 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4063. Min Range: -5.4063
Max Act: 4.9063. Min Act: -0.1700
Data Index: 8821534 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4063. Min Range: -5.4063
Max Act: 4.9063. Min Act: -0.1700
Data Index: 1736204 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4063. Min Range: -5.4063
Max Act: 4.8751. Min Act: -0.1700
Data Index: 405507 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4063. Min Range: -5.4063
Max Act: 4.8751. Min Act: -0.1700
Data Index: 8256680 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #19