Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2917 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5107. Min Range: -8.5107
Max Act: 8.5107. Min Act: -0.1700
Data Index: 4744885 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5107. Min Range: -8.5107
Max Act: 8.3232. Min Act: -0.1700
Data Index: 3592301 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5107. Min Range: -8.5107
Max Act: 8.2607. Min Act: -0.1700
Data Index: 4358128 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5107. Min Range: -8.5107
Max Act: 8.1670. Min Act: -0.1700
Data Index: 5563942 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5107. Min Range: -8.5107
Max Act: 8.1045. Min Act: -0.1700
Data Index: 528 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5107. Min Range: -8.5107
Max Act: 8.1045. Min Act: -0.1700
Data Index: 7233250 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5107. Min Range: -8.5107
Max Act: 8.1357. Min Act: -0.1700
Data Index: 134998 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5107. Min Range: -8.5107
Max Act: 8.0107. Min Act: -0.1700
Data Index: 266531 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5107. Min Range: -8.5107
Max Act: 8.0107. Min Act: -0.1700
Data Index: 7797614 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5107. Min Range: -8.5107
Max Act: 8.0107. Min Act: -0.1700
Data Index: 623891 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5107. Min Range: -8.5107
Max Act: 7.9795. Min Act: -0.1700
Data Index: 5156013 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5107. Min Range: -8.5107
Max Act: 7.9482. Min Act: -0.1700
Data Index: 210207 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5107. Min Range: -8.5107
Max Act: 7.9795. Min Act: -0.1700
Data Index: 5434019 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5107. Min Range: -8.5107
Max Act: 7.9482. Min Act: -0.1700
Data Index: 3387581 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5107. Min Range: -8.5107
Max Act: 7.9482. Min Act: -0.1700
Data Index: 3768776 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5107. Min Range: -8.5107
Max Act: 7.9482. Min Act: -0.1700
Data Index: 5986009 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5107. Min Range: -8.5107
Max Act: 7.9170. Min Act: -0.1700
Data Index: 778360 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5107. Min Range: -8.5107
Max Act: 7.9170. Min Act: -0.1700
Data Index: 903739 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5107. Min Range: -8.5107
Max Act: 7.8545. Min Act: -0.1700
Data Index: 3424630 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5107. Min Range: -8.5107
Max Act: 7.8857. Min Act: -0.1700
Data Index: 506686 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19