Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1122 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6995. Min Range: -9.6995
Max Act: 9.6995. Min Act: -0.1700
Data Index: 6557236 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6995. Min Range: -9.6995
Max Act: 9.6995. Min Act: -0.1700
Data Index: 1180291 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6995. Min Range: -9.6995
Max Act: 9.6995. Min Act: -0.1700
Data Index: 1163629 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6995. Min Range: -9.6995
Max Act: 9.5745. Min Act: -0.1700
Data Index: 2278786 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6995. Min Range: -9.6995
Max Act: 9.5120. Min Act: -0.1700
Data Index: 7797933 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6995. Min Range: -9.6995
Max Act: 9.3870. Min Act: -0.1700
Data Index: 7158904 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6995. Min Range: -9.6995
Max Act: 9.3870. Min Act: -0.1700
Data Index: 3187155 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6995. Min Range: -9.6995
Max Act: 9.3245. Min Act: -0.1700
Data Index: 842833 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6995. Min Range: -9.6995
Max Act: 9.3245. Min Act: -0.1700
Data Index: 558712 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6995. Min Range: -9.6995
Max Act: 9.3870. Min Act: -0.1700
Data Index: 860373 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6995. Min Range: -9.6995
Max Act: 9.3245. Min Act: -0.1700
Data Index: 5380798 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6995. Min Range: -9.6995
Max Act: 9.3245. Min Act: -0.1700
Data Index: 8291510 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6995. Min Range: -9.6995
Max Act: 9.3245. Min Act: -0.1700
Data Index: 3677032 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6995. Min Range: -9.6995
Max Act: 9.2620. Min Act: -0.1700
Data Index: 3414549 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6995. Min Range: -9.6995
Max Act: 9.3245. Min Act: -0.1700
Data Index: 8291508 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6995. Min Range: -9.6995
Max Act: 9.2620. Min Act: -0.1700
Data Index: 4483359 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6995. Min Range: -9.6995
Max Act: 9.2620. Min Act: -0.1700
Data Index: 5495668 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6995. Min Range: -9.6995
Max Act: 9.2620. Min Act: -0.1700
Data Index: 5885190 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6995. Min Range: -9.6995
Max Act: 9.2620. Min Act: -0.1700
Data Index: 6118174 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6995. Min Range: -9.6995
Max Act: 9.2620. Min Act: -0.1700
Data Index: 6140064 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #19