Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1561 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7691. Min Range: -8.7691
Max Act: 8.7691. Min Act: -0.1700
Data Index: 247847 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7691. Min Range: -8.7691
Max Act: 8.3316. Min Act: -0.1700
Data Index: 670173 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7691. Min Range: -8.7691
Max Act: 8.3316. Min Act: -0.1700
Data Index: 3215477 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7691. Min Range: -8.7691
Max Act: 8.0816. Min Act: -0.1700
Data Index: 5527116 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7691. Min Range: -8.7691
Max Act: 7.9566. Min Act: -0.1700
Data Index: 3751646 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7691. Min Range: -8.7691
Max Act: 7.9566. Min Act: -0.1700
Data Index: 6555465 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7691. Min Range: -8.7691
Max Act: 7.8941. Min Act: -0.1700
Data Index: 542247 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7691. Min Range: -8.7691
Max Act: 7.8941. Min Act: -0.1700
Data Index: 1194140 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7691. Min Range: -8.7691
Max Act: 7.8941. Min Act: -0.1700
Data Index: 4558338 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7691. Min Range: -8.7691
Max Act: 7.8316. Min Act: -0.1700
Data Index: 4325290 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7691. Min Range: -8.7691
Max Act: 7.8316. Min Act: -0.1700
Data Index: 5757250 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7691. Min Range: -8.7691
Max Act: 7.8316. Min Act: -0.1700
Data Index: 5961505 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7691. Min Range: -8.7691
Max Act: 7.7691. Min Act: -0.1700
Data Index: 4118362 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7691. Min Range: -8.7691
Max Act: 7.7691. Min Act: -0.1700
Data Index: 4522022 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7691. Min Range: -8.7691
Max Act: 7.7691. Min Act: -0.1700
Data Index: 4957033 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7691. Min Range: -8.7691
Max Act: 7.7066. Min Act: -0.1700
Data Index: 5206196 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7691. Min Range: -8.7691
Max Act: 7.7066. Min Act: -0.1700
Data Index: 6665529 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7691. Min Range: -8.7691
Max Act: 7.7066. Min Act: -0.1700
Data Index: 8480042 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7691. Min Range: -8.7691
Max Act: 7.7066. Min Act: -0.1700
Data Index: 1721027 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7691. Min Range: -8.7691
Max Act: 7.7066. Min Act: -0.1700
Data Index: 8609889 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19