Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3377 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0521. Min Range: -8.0521
Max Act: 8.0521. Min Act: -0.1700
Data Index: 4041654 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0521. Min Range: -8.0521
Max Act: 8.0521. Min Act: -0.1700
Data Index: 2203290 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0521. Min Range: -8.0521
Max Act: 8.0521. Min Act: -0.1700
Data Index: 4659618 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0521. Min Range: -8.0521
Max Act: 7.9896. Min Act: -0.1700
Data Index: 3241639 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0521. Min Range: -8.0521
Max Act: 7.8646. Min Act: -0.1700
Data Index: 6156332 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0521. Min Range: -8.0521
Max Act: 7.7709. Min Act: -0.1700
Data Index: 6559508 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0521. Min Range: -8.0521
Max Act: 7.7396. Min Act: -0.1700
Data Index: 657923 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0521. Min Range: -8.0521
Max Act: 7.6771. Min Act: -0.1700
Data Index: 5782147 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0521. Min Range: -8.0521
Max Act: 7.5834. Min Act: -0.1700
Data Index: 4165386 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0521. Min Range: -8.0521
Max Act: 7.5209. Min Act: -0.1700
Data Index: 2401020 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0521. Min Range: -8.0521
Max Act: 7.5521. Min Act: -0.1700
Data Index: 7498507 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0521. Min Range: -8.0521
Max Act: 7.5209. Min Act: -0.1700
Data Index: 890064 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0521. Min Range: -8.0521
Max Act: 7.4896. Min Act: -0.1700
Data Index: 353939 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0521. Min Range: -8.0521
Max Act: 7.5521. Min Act: -0.1700
Data Index: 6456659 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0521. Min Range: -8.0521
Max Act: 7.5209. Min Act: -0.1700
Data Index: 4219337 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0521. Min Range: -8.0521
Max Act: 7.4584. Min Act: -0.1700
Data Index: 8136071 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0521. Min Range: -8.0521
Max Act: 7.4584. Min Act: -0.1700
Data Index: 3050973 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0521. Min Range: -8.0521
Max Act: 7.4271. Min Act: -0.1700
Data Index: 2401029 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0521. Min Range: -8.0521
Max Act: 7.4271. Min Act: -0.1700
Data Index: 7825210 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0521. Min Range: -8.0521
Max Act: 7.4271. Min Act: -0.1700
Data Index: 2401024 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #19