Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6145 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.5065. Min Act: -0.1700
Data Index: 215136 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.4127. Min Act: -0.1700
Data Index: 7761287 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.4127. Min Act: -0.1700
Data Index: 1940668 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.3502. Min Act: -0.1700
Data Index: 4733601 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.3189. Min Act: -0.1700
Data Index: 2205550 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.3189. Min Act: -0.1700
Data Index: 2246418 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.2877. Min Act: -0.1700
Data Index: 2857876 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.2877. Min Act: -0.1700
Data Index: 2989702 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.2877. Min Act: -0.1700
Data Index: 8282700 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.2877. Min Act: -0.1700
Data Index: 2592446 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.2877. Min Act: -0.1700
Data Index: 3103022 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.2877. Min Act: -0.1700
Data Index: 2091924 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.2877. Min Act: -0.1700
Data Index: 4136143 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.2564. Min Act: -0.1700
Data Index: 4447620 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.2252. Min Act: -0.1700
Data Index: 699674 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.2564. Min Act: -0.1700
Data Index: 6984986 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.2564. Min Act: -0.1700
Data Index: 2091923 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.2564. Min Act: -0.1700
Data Index: 3392398 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.2564. Min Act: -0.1700
Data Index: 5535725 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5065. Min Range: -4.5065
Max Act: 4.2564. Min Act: -0.1700
Data Index: 5373368 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19