Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2275 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6858. Min Range: -6.6858
Max Act: 6.6858. Min Act: -0.1700
Data Index: 1107666 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6858. Min Range: -6.6858
Max Act: 5.9670. Min Act: -0.1700
Data Index: 5093631 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6858. Min Range: -6.6858
Max Act: 5.8733. Min Act: -0.1700
Data Index: 8391399 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6858. Min Range: -6.6858
Max Act: 5.8420. Min Act: -0.1700
Data Index: 1737136 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6858. Min Range: -6.6858
Max Act: 5.8108. Min Act: -0.1700
Data Index: 4327874 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6858. Min Range: -6.6858
Max Act: 5.7795. Min Act: -0.1700
Data Index: 5212569 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6858. Min Range: -6.6858
Max Act: 5.7483. Min Act: -0.1700
Data Index: 7255574 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6858. Min Range: -6.6858
Max Act: 5.7483. Min Act: -0.1700
Data Index: 7692158 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6858. Min Range: -6.6858
Max Act: 5.7170. Min Act: -0.1700
Data Index: 5798223 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6858. Min Range: -6.6858
Max Act: 5.6858. Min Act: -0.1700
Data Index: 903030 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6858. Min Range: -6.6858
Max Act: 5.6858. Min Act: -0.1700
Data Index: 2019417 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6858. Min Range: -6.6858
Max Act: 5.6858. Min Act: -0.1700
Data Index: 4773915 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6858. Min Range: -6.6858
Max Act: 5.6233. Min Act: -0.1700
Data Index: 2481828 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6858. Min Range: -6.6858
Max Act: 5.6233. Min Act: -0.1700
Data Index: 3602022 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6858. Min Range: -6.6858
Max Act: 5.6233. Min Act: -0.1700
Data Index: 2017055 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6858. Min Range: -6.6858
Max Act: 5.5920. Min Act: -0.1700
Data Index: 7086538 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6858. Min Range: -6.6858
Max Act: 5.5920. Min Act: -0.1700
Data Index: 8294907 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6858. Min Range: -6.6858
Max Act: 5.5608. Min Act: -0.1700
Data Index: 1725938 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6858. Min Range: -6.6858
Max Act: 5.5608. Min Act: -0.1700
Data Index: 6101193 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6858. Min Range: -6.6858
Max Act: 5.5295. Min Act: -0.1700
Data Index: 6289516 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19