Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3459 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8001. Min Range: -6.8001
Max Act: 6.8001. Min Act: -0.1700
Data Index: 1222299 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8001. Min Range: -6.8001
Max Act: 6.7688. Min Act: -0.1700
Data Index: 6274052 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8001. Min Range: -6.8001
Max Act: 6.6751. Min Act: -0.1700
Data Index: 3612063 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8001. Min Range: -6.8001
Max Act: 6.6438. Min Act: -0.1700
Data Index: 2868368 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8001. Min Range: -6.8001
Max Act: 6.6751. Min Act: -0.1700
Data Index: 345033 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8001. Min Range: -6.8001
Max Act: 6.5813. Min Act: -0.1700
Data Index: 2499795 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8001. Min Range: -6.8001
Max Act: 6.5188. Min Act: -0.1700
Data Index: 66719 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8001. Min Range: -6.8001
Max Act: 6.5188. Min Act: -0.1700
Data Index: 2074838 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8001. Min Range: -6.8001
Max Act: 6.5501. Min Act: -0.1700
Data Index: 8151209 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8001. Min Range: -6.8001
Max Act: 6.5188. Min Act: -0.1700
Data Index: 4482571 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8001. Min Range: -6.8001
Max Act: 6.4876. Min Act: -0.1700
Data Index: 8825665 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8001. Min Range: -6.8001
Max Act: 6.4876. Min Act: -0.1700
Data Index: 2366044 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8001. Min Range: -6.8001
Max Act: 6.4563. Min Act: -0.1700
Data Index: 3275300 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8001. Min Range: -6.8001
Max Act: 6.4251. Min Act: -0.1700
Data Index: 6010048 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8001. Min Range: -6.8001
Max Act: 6.4563. Min Act: -0.1700
Data Index: 6880239 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8001. Min Range: -6.8001
Max Act: 6.4563. Min Act: -0.1700
Data Index: 137372 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8001. Min Range: -6.8001
Max Act: 6.4563. Min Act: -0.1700
Data Index: 5227610 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8001. Min Range: -6.8001
Max Act: 6.4563. Min Act: -0.1700
Data Index: 5109069 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8001. Min Range: -6.8001
Max Act: 6.4563. Min Act: -0.1700
Data Index: 4102968 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8001. Min Range: -6.8001
Max Act: 6.4251. Min Act: -0.1700
Data Index: 4598485 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19