Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5313 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.7281. Min Range: -15.7281
Max Act: 15.7281. Min Act: -0.1700
Data Index: 3119152 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.7281. Min Range: -15.7281
Max Act: 15.3531. Min Act: -0.1700
Data Index: 6489805 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.7281. Min Range: -15.7281
Max Act: 15.3531. Min Act: -0.1700
Data Index: 5537150 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.7281. Min Range: -15.7281
Max Act: 15.2906. Min Act: -0.1700
Data Index: 4519511 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.7281. Min Range: -15.7281
Max Act: 15.2906. Min Act: -0.1700
Data Index: 4703895 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.7281. Min Range: -15.7281
Max Act: 15.2906. Min Act: -0.1700
Data Index: 1945180 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.7281. Min Range: -15.7281
Max Act: 15.1656. Min Act: -0.1700
Data Index: 4703909 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.7281. Min Range: -15.7281
Max Act: 15.1031. Min Act: -0.1700
Data Index: 3547259 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.7281. Min Range: -15.7281
Max Act: 15.1031. Min Act: -0.1700
Data Index: 1269302 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.7281. Min Range: -15.7281
Max Act: 15.1031. Min Act: -0.1700
Data Index: 6810198 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.7281. Min Range: -15.7281
Max Act: 14.9781. Min Act: -0.1700
Data Index: 3649057 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.7281. Min Range: -15.7281
Max Act: 14.9156. Min Act: -0.1700
Data Index: 8620732 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.7281. Min Range: -15.7281
Max Act: 14.9781. Min Act: -0.1700
Data Index: 8510125 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.7281. Min Range: -15.7281
Max Act: 14.9156. Min Act: -0.1700
Data Index: 152838 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.7281. Min Range: -15.7281
Max Act: 14.7906. Min Act: -0.1700
Data Index: 7316362 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.7281. Min Range: -15.7281
Max Act: 14.7906. Min Act: -0.1700
Data Index: 7367187 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.7281. Min Range: -15.7281
Max Act: 14.8531. Min Act: -0.1700
Data Index: 7566939 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.7281. Min Range: -15.7281
Max Act: 14.8531. Min Act: -0.1700
Data Index: 3194407 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.7281. Min Range: -15.7281
Max Act: 14.7906. Min Act: -0.1700
Data Index: 2256234 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.7281. Min Range: -15.7281
Max Act: 14.8531. Min Act: -0.1700
Data Index: 6489806 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #19