Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1026 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1856. Min Range: -6.1856
Max Act: 6.1856. Min Act: -0.1700
Data Index: 629187 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1856. Min Range: -6.1856
Max Act: 6.1231. Min Act: -0.1700
Data Index: 8820451 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1856. Min Range: -6.1856
Max Act: 6.1231. Min Act: -0.1700
Data Index: 4947728 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1856. Min Range: -6.1856
Max Act: 6.1231. Min Act: -0.1700
Data Index: 1825696 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1856. Min Range: -6.1856
Max Act: 6.1231. Min Act: -0.1700
Data Index: 4587410 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1856. Min Range: -6.1856
Max Act: 6.0919. Min Act: -0.1700
Data Index: 8204794 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1856. Min Range: -6.1856
Max Act: 5.9981. Min Act: -0.1700
Data Index: 3479088 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1856. Min Range: -6.1856
Max Act: 5.9669. Min Act: -0.1700
Data Index: 6945552 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1856. Min Range: -6.1856
Max Act: 5.9981. Min Act: -0.1700
Data Index: 7392215 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1856. Min Range: -6.1856
Max Act: 5.9981. Min Act: -0.1700
Data Index: 7258543 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1856. Min Range: -6.1856
Max Act: 5.9669. Min Act: -0.1700
Data Index: 7537568 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1856. Min Range: -6.1856
Max Act: 5.9669. Min Act: -0.1700
Data Index: 5083442 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1856. Min Range: -6.1856
Max Act: 5.9669. Min Act: -0.1700
Data Index: 4658786 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1856. Min Range: -6.1856
Max Act: 5.9669. Min Act: -0.1700
Data Index: 1346922 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1856. Min Range: -6.1856
Max Act: 5.9356. Min Act: -0.1700
Data Index: 5715860 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1856. Min Range: -6.1856
Max Act: 5.9669. Min Act: -0.1700
Data Index: 5133813 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1856. Min Range: -6.1856
Max Act: 5.9356. Min Act: -0.1700
Data Index: 6580974 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1856. Min Range: -6.1856
Max Act: 5.9044. Min Act: -0.1700
Data Index: 3136491 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1856. Min Range: -6.1856
Max Act: 5.8731. Min Act: -0.1700
Data Index: 8590369 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1856. Min Range: -6.1856
Max Act: 5.8731. Min Act: -0.1700
Data Index: 1556201 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19