Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5291 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5686. Min Range: -7.5686
Max Act: 7.5686. Min Act: -0.1700
Data Index: 8719955 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5686. Min Range: -7.5686
Max Act: 7.0998. Min Act: -0.1700
Data Index: 7307419 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5686. Min Range: -7.5686
Max Act: 6.9436. Min Act: -0.1700
Data Index: 2643841 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5686. Min Range: -7.5686
Max Act: 6.9436. Min Act: -0.1700
Data Index: 6443238 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5686. Min Range: -7.5686
Max Act: 6.8498. Min Act: -0.1700
Data Index: 5045130 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5686. Min Range: -7.5686
Max Act: 6.8498. Min Act: -0.1700
Data Index: 5374292 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5686. Min Range: -7.5686
Max Act: 6.8186. Min Act: -0.1700
Data Index: 6448185 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5686. Min Range: -7.5686
Max Act: 6.8186. Min Act: -0.1700
Data Index: 8747076 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5686. Min Range: -7.5686
Max Act: 6.7561. Min Act: -0.1700
Data Index: 2086016 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5686. Min Range: -7.5686
Max Act: 6.7873. Min Act: -0.1700
Data Index: 7475664 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5686. Min Range: -7.5686
Max Act: 6.8186. Min Act: -0.1700
Data Index: 6222027 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5686. Min Range: -7.5686
Max Act: 6.7561. Min Act: -0.1700
Data Index: 927713 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5686. Min Range: -7.5686
Max Act: 6.7248. Min Act: -0.1700
Data Index: 5428752 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5686. Min Range: -7.5686
Max Act: 6.6936. Min Act: -0.1700
Data Index: 6264318 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5686. Min Range: -7.5686
Max Act: 6.6623. Min Act: -0.1700
Data Index: 3649266 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5686. Min Range: -7.5686
Max Act: 6.6311. Min Act: -0.1700
Data Index: 406265 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5686. Min Range: -7.5686
Max Act: 6.5998. Min Act: -0.1700
Data Index: 1621772 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5686. Min Range: -7.5686
Max Act: 6.5998. Min Act: -0.1700
Data Index: 2530943 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5686. Min Range: -7.5686
Max Act: 6.5686. Min Act: -0.1700
Data Index: 3916269 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5686. Min Range: -7.5686
Max Act: 6.5686. Min Act: -0.1700
Data Index: 8628263 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19