Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2547 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5347. Min Range: -6.5347
Max Act: 6.5347. Min Act: -0.1700
Data Index: 7013444 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5347. Min Range: -6.5347
Max Act: 6.4722. Min Act: -0.1700
Data Index: 3156605 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5347. Min Range: -6.5347
Max Act: 6.0972. Min Act: -0.1700
Data Index: 67932 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5347. Min Range: -6.5347
Max Act: 5.9097. Min Act: -0.1700
Data Index: 6590843 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5347. Min Range: -6.5347
Max Act: 5.7535. Min Act: -0.1700
Data Index: 129080 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5347. Min Range: -6.5347
Max Act: 5.7222. Min Act: -0.1700
Data Index: 7331110 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5347. Min Range: -6.5347
Max Act: 5.5972. Min Act: -0.1700
Data Index: 777545 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5347. Min Range: -6.5347
Max Act: 5.6285. Min Act: -0.1700
Data Index: 4677263 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5347. Min Range: -6.5347
Max Act: 5.6285. Min Act: -0.1700
Data Index: 710338 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5347. Min Range: -6.5347
Max Act: 5.5972. Min Act: -0.1700
Data Index: 8392467 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5347. Min Range: -6.5347
Max Act: 5.5972. Min Act: -0.1700
Data Index: 3151783 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5347. Min Range: -6.5347
Max Act: 5.5972. Min Act: -0.1700
Data Index: 7380682 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5347. Min Range: -6.5347
Max Act: 5.5972. Min Act: -0.1700
Data Index: 2170322 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5347. Min Range: -6.5347
Max Act: 5.5972. Min Act: -0.1700
Data Index: 844956 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5347. Min Range: -6.5347
Max Act: 5.5972. Min Act: -0.1700
Data Index: 3086574 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5347. Min Range: -6.5347
Max Act: 5.5660. Min Act: -0.1700
Data Index: 3481515 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5347. Min Range: -6.5347
Max Act: 5.5347. Min Act: -0.1700
Data Index: 7823518 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5347. Min Range: -6.5347
Max Act: 5.5660. Min Act: -0.1700
Data Index: 7501926 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5347. Min Range: -6.5347
Max Act: 5.5660. Min Act: -0.1700
Data Index: 5506563 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5347. Min Range: -6.5347
Max Act: 5.5347. Min Act: -0.1700
Data Index: 7879108 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19