Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2054 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9523. Min Range: -6.9523
Max Act: 6.9523. Min Act: -0.1700
Data Index: 4303787 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9523. Min Range: -6.9523
Max Act: 6.9523. Min Act: -0.1700
Data Index: 7149261 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9523. Min Range: -6.9523
Max Act: 6.7335. Min Act: -0.1700
Data Index: 7781852 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9523. Min Range: -6.9523
Max Act: 6.7648. Min Act: -0.1700
Data Index: 794601 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9523. Min Range: -6.9523
Max Act: 6.7335. Min Act: -0.1700
Data Index: 5262643 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9523. Min Range: -6.9523
Max Act: 6.6085. Min Act: -0.1700
Data Index: 8187783 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9523. Min Range: -6.9523
Max Act: 6.6085. Min Act: -0.1700
Data Index: 133209 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9523. Min Range: -6.9523
Max Act: 6.5773. Min Act: -0.1700
Data Index: 329268 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9523. Min Range: -6.9523
Max Act: 6.5773. Min Act: -0.1700
Data Index: 6534058 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9523. Min Range: -6.9523
Max Act: 6.5460. Min Act: -0.1700
Data Index: 65028 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9523. Min Range: -6.9523
Max Act: 6.4835. Min Act: -0.1700
Data Index: 3335795 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9523. Min Range: -6.9523
Max Act: 6.4523. Min Act: -0.1700
Data Index: 3691695 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9523. Min Range: -6.9523
Max Act: 6.4835. Min Act: -0.1700
Data Index: 1908376 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9523. Min Range: -6.9523
Max Act: 6.4210. Min Act: -0.1700
Data Index: 1341538 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9523. Min Range: -6.9523
Max Act: 6.4523. Min Act: -0.1700
Data Index: 5783716 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9523. Min Range: -6.9523
Max Act: 6.4210. Min Act: -0.1700
Data Index: 722916 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9523. Min Range: -6.9523
Max Act: 6.3898. Min Act: -0.1700
Data Index: 7196770 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9523. Min Range: -6.9523
Max Act: 6.3898. Min Act: -0.1700
Data Index: 2783050 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9523. Min Range: -6.9523
Max Act: 6.3898. Min Act: -0.1700
Data Index: 6051324 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9523. Min Range: -6.9523
Max Act: 6.3898. Min Act: -0.1700
Data Index: 1092779 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #19