Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2522 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.5828. Min Range: -8.5828
Max Act: 8.5828. Min Act: -0.1700
Data Index: 1598352 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5828. Min Range: -8.5828
Max Act: 8.5203. Min Act: -0.1700
Data Index: 8637361 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5828. Min Range: -8.5828
Max Act: 8.5203. Min Act: -0.1700
Data Index: 250044 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5828. Min Range: -8.5828
Max Act: 8.3953. Min Act: -0.1700
Data Index: 2640133 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5828. Min Range: -8.5828
Max Act: 8.3953. Min Act: -0.1700
Data Index: 370423 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5828. Min Range: -8.5828
Max Act: 8.3953. Min Act: -0.1700
Data Index: 5501948 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5828. Min Range: -8.5828
Max Act: 8.3328. Min Act: -0.1700
Data Index: 2942531 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5828. Min Range: -8.5828
Max Act: 8.3328. Min Act: -0.1700
Data Index: 3757519 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5828. Min Range: -8.5828
Max Act: 8.2703. Min Act: -0.1700
Data Index: 6930194 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5828. Min Range: -8.5828
Max Act: 8.2703. Min Act: -0.1700
Data Index: 8114426 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5828. Min Range: -8.5828
Max Act: 8.2703. Min Act: -0.1700
Data Index: 3980934 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5828. Min Range: -8.5828
Max Act: 8.2078. Min Act: -0.1700
Data Index: 6259146 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5828. Min Range: -8.5828
Max Act: 8.2078. Min Act: -0.1700
Data Index: 349809 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5828. Min Range: -8.5828
Max Act: 8.1453. Min Act: -0.1700
Data Index: 5564632 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5828. Min Range: -8.5828
Max Act: 8.2078. Min Act: -0.1700
Data Index: 1826758 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5828. Min Range: -8.5828
Max Act: 8.2078. Min Act: -0.1700
Data Index: 3117137 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5828. Min Range: -8.5828
Max Act: 8.2078. Min Act: -0.1700
Data Index: 7079503 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5828. Min Range: -8.5828
Max Act: 8.2078. Min Act: -0.1700
Data Index: 6335356 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5828. Min Range: -8.5828
Max Act: 8.2078. Min Act: -0.1700
Data Index: 6128875 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5828. Min Range: -8.5828
Max Act: 8.1453. Min Act: -0.1700
Data Index: 3731852 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19