Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2939 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6783. Min Range: -2.6783
Max Act: 2.6783. Min Act: -0.1700
Data Index: 1982841 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6783. Min Range: -2.6783
Max Act: 2.6141. Min Act: -0.1700
Data Index: 1959643 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6783. Min Range: -2.6783
Max Act: 2.5980. Min Act: -0.1700
Data Index: 4504276 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6783. Min Range: -2.6783
Max Act: 2.5657. Min Act: -0.1700
Data Index: 4224658 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6783. Min Range: -2.6783
Max Act: 2.5496. Min Act: -0.1700
Data Index: 7157120 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6783. Min Range: -2.6783
Max Act: 2.5496. Min Act: -0.1700
Data Index: 4642800 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6783. Min Range: -2.6783
Max Act: 2.5334. Min Act: -0.1700
Data Index: 1276966 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6783. Min Range: -2.6783
Max Act: 2.5334. Min Act: -0.1700
Data Index: 2020463 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6783. Min Range: -2.6783
Max Act: 2.5173. Min Act: -0.1700
Data Index: 5508174 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6783. Min Range: -2.6783
Max Act: 2.5173. Min Act: -0.1700
Data Index: 4224659 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6783. Min Range: -2.6783
Max Act: 2.5173. Min Act: -0.1700
Data Index: 7045526 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6783. Min Range: -2.6783
Max Act: 2.5173. Min Act: -0.1700
Data Index: 993407 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6783. Min Range: -2.6783
Max Act: 2.5011. Min Act: -0.1700
Data Index: 1004964 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6783. Min Range: -2.6783
Max Act: 2.5011. Min Act: -0.1700
Data Index: 4740938 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6783. Min Range: -2.6783
Max Act: 2.5011. Min Act: -0.1700
Data Index: 6184674 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6783. Min Range: -2.6783
Max Act: 2.4849. Min Act: -0.1700
Data Index: 332018 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6783. Min Range: -2.6783
Max Act: 2.4849. Min Act: -0.1700
Data Index: 5943193 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6783. Min Range: -2.6783
Max Act: 2.4849. Min Act: -0.1700
Data Index: 1315633 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6783. Min Range: -2.6783
Max Act: 2.4849. Min Act: -0.1700
Data Index: 3600482 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6783. Min Range: -2.6783
Max Act: 2.4849. Min Act: -0.1700
Data Index: 435444 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19