Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 689 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6675. Min Range: -5.6675
Max Act: 5.6675. Min Act: -0.1700
Data Index: 6286550 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6675. Min Range: -5.6675
Max Act: 5.5425. Min Act: -0.1700
Data Index: 483647 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6675. Min Range: -5.6675
Max Act: 5.5425. Min Act: -0.1700
Data Index: 6378341 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6675. Min Range: -5.6675
Max Act: 5.4487. Min Act: -0.1700
Data Index: 3591534 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6675. Min Range: -5.6675
Max Act: 5.4487. Min Act: -0.1700
Data Index: 2165387 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6675. Min Range: -5.6675
Max Act: 5.3550. Min Act: -0.1700
Data Index: 5392509 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6675. Min Range: -5.6675
Max Act: 5.3550. Min Act: -0.1700
Data Index: 6025395 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6675. Min Range: -5.6675
Max Act: 5.2925. Min Act: -0.1700
Data Index: 1335732 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6675. Min Range: -5.6675
Max Act: 5.2925. Min Act: -0.1700
Data Index: 2257150 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6675. Min Range: -5.6675
Max Act: 5.2612. Min Act: -0.1700
Data Index: 4380911 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6675. Min Range: -5.6675
Max Act: 5.1675. Min Act: -0.1700
Data Index: 4298830 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6675. Min Range: -5.6675
Max Act: 5.1987. Min Act: -0.1700
Data Index: 2003393 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6675. Min Range: -5.6675
Max Act: 5.1987. Min Act: -0.1700
Data Index: 6681154 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6675. Min Range: -5.6675
Max Act: 5.1987. Min Act: -0.1700
Data Index: 760541 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6675. Min Range: -5.6675
Max Act: 5.1675. Min Act: -0.1700
Data Index: 3467649 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6675. Min Range: -5.6675
Max Act: 5.1675. Min Act: -0.1700
Data Index: 817640 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6675. Min Range: -5.6675
Max Act: 5.1675. Min Act: -0.1700
Data Index: 5484998 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6675. Min Range: -5.6675
Max Act: 5.1675. Min Act: -0.1700
Data Index: 2209577 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6675. Min Range: -5.6675
Max Act: 5.1675. Min Act: -0.1700
Data Index: 4339937 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6675. Min Range: -5.6675
Max Act: 5.1675. Min Act: -0.1700
Data Index: 5972304 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19