Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 481 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6977. Min Range: -6.6977
Max Act: 6.6977. Min Act: -0.1700
Data Index: 5530193 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6977. Min Range: -6.6977
Max Act: 6.6977. Min Act: -0.1700
Data Index: 5089369 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6977. Min Range: -6.6977
Max Act: 6.6664. Min Act: -0.1700
Data Index: 2898243 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6977. Min Range: -6.6977
Max Act: 6.6352. Min Act: -0.1700
Data Index: 7395829 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6977. Min Range: -6.6977
Max Act: 6.5727. Min Act: -0.1700
Data Index: 6137445 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6977. Min Range: -6.6977
Max Act: 6.5414. Min Act: -0.1700
Data Index: 7200482 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6977. Min Range: -6.6977
Max Act: 6.5414. Min Act: -0.1700
Data Index: 4957667 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6977. Min Range: -6.6977
Max Act: 6.4789. Min Act: -0.1700
Data Index: 1247845 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6977. Min Range: -6.6977
Max Act: 6.4789. Min Act: -0.1700
Data Index: 3038718 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6977. Min Range: -6.6977
Max Act: 6.4164. Min Act: -0.1700
Data Index: 2773494 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6977. Min Range: -6.6977
Max Act: 6.3539. Min Act: -0.1700
Data Index: 1784684 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6977. Min Range: -6.6977
Max Act: 6.3227. Min Act: -0.1700
Data Index: 2038538 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6977. Min Range: -6.6977
Max Act: 6.3227. Min Act: -0.1700
Data Index: 6423785 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6977. Min Range: -6.6977
Max Act: 6.2602. Min Act: -0.1700
Data Index: 2741620 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6977. Min Range: -6.6977
Max Act: 6.2914. Min Act: -0.1700
Data Index: 357504 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6977. Min Range: -6.6977
Max Act: 6.2602. Min Act: -0.1700
Data Index: 7735087 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6977. Min Range: -6.6977
Max Act: 6.2602. Min Act: -0.1700
Data Index: 5513051 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6977. Min Range: -6.6977
Max Act: 6.2289. Min Act: -0.1700
Data Index: 651186 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6977. Min Range: -6.6977
Max Act: 6.2289. Min Act: -0.1700
Data Index: 7852403 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6977. Min Range: -6.6977
Max Act: 6.2289. Min Act: -0.1700
Data Index: 2993185 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #19