Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2757 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3787. Min Range: -8.3787
Max Act: 8.3787. Min Act: -0.1700
Data Index: 291663 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3787. Min Range: -8.3787
Max Act: 8.3162. Min Act: -0.1700
Data Index: 1187832 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3787. Min Range: -8.3787
Max Act: 7.9412. Min Act: -0.1700
Data Index: 4307144 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3787. Min Range: -8.3787
Max Act: 7.8474. Min Act: -0.1700
Data Index: 1187831 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3787. Min Range: -8.3787
Max Act: 7.7537. Min Act: -0.1700
Data Index: 5304007 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3787. Min Range: -8.3787
Max Act: 7.7537. Min Act: -0.1700
Data Index: 2277633 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3787. Min Range: -8.3787
Max Act: 7.7849. Min Act: -0.1700
Data Index: 3266953 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3787. Min Range: -8.3787
Max Act: 7.7537. Min Act: -0.1700
Data Index: 7476134 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3787. Min Range: -8.3787
Max Act: 7.5662. Min Act: -0.1700
Data Index: 8728975 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3787. Min Range: -8.3787
Max Act: 7.5662. Min Act: -0.1700
Data Index: 4573910 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3787. Min Range: -8.3787
Max Act: 7.5974. Min Act: -0.1700
Data Index: 4631258 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3787. Min Range: -8.3787
Max Act: 7.5974. Min Act: -0.1700
Data Index: 7122275 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3787. Min Range: -8.3787
Max Act: 7.5037. Min Act: -0.1700
Data Index: 2326307 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3787. Min Range: -8.3787
Max Act: 7.4412. Min Act: -0.1700
Data Index: 3859241 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3787. Min Range: -8.3787
Max Act: 7.4412. Min Act: -0.1700
Data Index: 1802101 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3787. Min Range: -8.3787
Max Act: 7.4099. Min Act: -0.1700
Data Index: 4420667 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3787. Min Range: -8.3787
Max Act: 7.3474. Min Act: -0.1700
Data Index: 4136869 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3787. Min Range: -8.3787
Max Act: 7.3162. Min Act: -0.1700
Data Index: 4387248 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3787. Min Range: -8.3787
Max Act: 7.2849. Min Act: -0.1700
Data Index: 4573912 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3787. Min Range: -8.3787
Max Act: 7.3162. Min Act: -0.1700
Data Index: 537155 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #19