Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 38 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6992. Min Range: -6.6992
Max Act: 6.6679. Min Act: -0.1700
Data Index: 8238233 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6992. Min Range: -6.6992
Max Act: 6.6992. Min Act: -0.1700
Data Index: 1188755 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6992. Min Range: -6.6992
Max Act: 6.3242. Min Act: -0.1700
Data Index: 4810826 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6992. Min Range: -6.6992
Max Act: 6.3242. Min Act: -0.1700
Data Index: 447225 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6992. Min Range: -6.6992
Max Act: 6.2929. Min Act: -0.1700
Data Index: 5519033 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6992. Min Range: -6.6992
Max Act: 6.2304. Min Act: -0.1700
Data Index: 3167097 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6992. Min Range: -6.6992
Max Act: 6.2304. Min Act: -0.1700
Data Index: 6067470 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6992. Min Range: -6.6992
Max Act: 6.2304. Min Act: -0.1700
Data Index: 1240072 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6992. Min Range: -6.6992
Max Act: 6.1992. Min Act: -0.1700
Data Index: 1025214 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6992. Min Range: -6.6992
Max Act: 6.1992. Min Act: -0.1700
Data Index: 4074941 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6992. Min Range: -6.6992
Max Act: 6.1679. Min Act: -0.1700
Data Index: 5574434 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6992. Min Range: -6.6992
Max Act: 6.1054. Min Act: -0.1700
Data Index: 3706580 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6992. Min Range: -6.6992
Max Act: 6.1054. Min Act: -0.1700
Data Index: 2623942 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6992. Min Range: -6.6992
Max Act: 6.1367. Min Act: -0.1700
Data Index: 6591673 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6992. Min Range: -6.6992
Max Act: 6.1054. Min Act: -0.1700
Data Index: 4138271 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6992. Min Range: -6.6992
Max Act: 6.1367. Min Act: -0.1700
Data Index: 6061928 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6992. Min Range: -6.6992
Max Act: 6.1367. Min Act: -0.1700
Data Index: 6064439 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6992. Min Range: -6.6992
Max Act: 6.0742. Min Act: -0.1700
Data Index: 6877951 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6992. Min Range: -6.6992
Max Act: 6.0742. Min Act: -0.1700
Data Index: 2760910 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6992. Min Range: -6.6992
Max Act: 6.0429. Min Act: -0.1700
Data Index: 5079727 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19