Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1782 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2584. Min Range: -8.2584
Max Act: 8.2584. Min Act: -0.1700
Data Index: 5426752 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2584. Min Range: -8.2584
Max Act: 8.1959. Min Act: -0.1700
Data Index: 8248016 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2584. Min Range: -8.2584
Max Act: 8.1334. Min Act: -0.1700
Data Index: 53763 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2584. Min Range: -8.2584
Max Act: 8.0709. Min Act: -0.1700
Data Index: 7790879 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2584. Min Range: -8.2584
Max Act: 7.9459. Min Act: -0.1700
Data Index: 496040 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2584. Min Range: -8.2584
Max Act: 7.9459. Min Act: -0.1700
Data Index: 1022815 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2584. Min Range: -8.2584
Max Act: 7.8834. Min Act: -0.1700
Data Index: 3078198 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2584. Min Range: -8.2584
Max Act: 7.8834. Min Act: -0.1700
Data Index: 8248027 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2584. Min Range: -8.2584
Max Act: 7.7896. Min Act: -0.1700
Data Index: 4482188 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2584. Min Range: -8.2584
Max Act: 7.7271. Min Act: -0.1700
Data Index: 3582594 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2584. Min Range: -8.2584
Max Act: 7.7584. Min Act: -0.1700
Data Index: 3347901 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2584. Min Range: -8.2584
Max Act: 7.7271. Min Act: -0.1700
Data Index: 7085299 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2584. Min Range: -8.2584
Max Act: 7.7584. Min Act: -0.1700
Data Index: 5909611 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2584. Min Range: -8.2584
Max Act: 7.6959. Min Act: -0.1700
Data Index: 949146 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2584. Min Range: -8.2584
Max Act: 7.6646. Min Act: -0.1700
Data Index: 8486506 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2584. Min Range: -8.2584
Max Act: 7.6334. Min Act: -0.1700
Data Index: 5796994 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2584. Min Range: -8.2584
Max Act: 7.6646. Min Act: -0.1700
Data Index: 4260059 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2584. Min Range: -8.2584
Max Act: 7.6021. Min Act: -0.1700
Data Index: 5444097 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2584. Min Range: -8.2584
Max Act: 7.6021. Min Act: -0.1700
Data Index: 1867856 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2584. Min Range: -8.2584
Max Act: 7.5709. Min Act: -0.1700
Data Index: 7832508 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #19