Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2565 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8154. Min Range: -10.8154
Max Act: 10.8154. Min Act: -0.1700
Data Index: 54759 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8154. Min Range: -10.8154
Max Act: 10.6904. Min Act: -0.1700
Data Index: 6115715 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8154. Min Range: -10.8154
Max Act: 10.6279. Min Act: -0.1700
Data Index: 4530453 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8154. Min Range: -10.8154
Max Act: 10.5654. Min Act: -0.1700
Data Index: 7955987 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8154. Min Range: -10.8154
Max Act: 10.5029. Min Act: -0.1700
Data Index: 5862386 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8154. Min Range: -10.8154
Max Act: 10.5654. Min Act: -0.1700
Data Index: 2836793 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8154. Min Range: -10.8154
Max Act: 10.4404. Min Act: -0.1700
Data Index: 2080365 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8154. Min Range: -10.8154
Max Act: 10.5029. Min Act: -0.1700
Data Index: 7470748 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8154. Min Range: -10.8154
Max Act: 10.4404. Min Act: -0.1700
Data Index: 8330055 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8154. Min Range: -10.8154
Max Act: 10.3154. Min Act: -0.1700
Data Index: 3915251 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8154. Min Range: -10.8154
Max Act: 10.3154. Min Act: -0.1700
Data Index: 6793387 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8154. Min Range: -10.8154
Max Act: 10.2529. Min Act: -0.1700
Data Index: 1015 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8154. Min Range: -10.8154
Max Act: 10.2529. Min Act: -0.1700
Data Index: 5386401 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8154. Min Range: -10.8154
Max Act: 10.2529. Min Act: -0.1700
Data Index: 1247380 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8154. Min Range: -10.8154
Max Act: 10.2529. Min Act: -0.1700
Data Index: 4715719 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8154. Min Range: -10.8154
Max Act: 10.1904. Min Act: -0.1700
Data Index: 4150376 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8154. Min Range: -10.8154
Max Act: 10.1904. Min Act: -0.1700
Data Index: 7910578 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8154. Min Range: -10.8154
Max Act: 10.1904. Min Act: -0.1700
Data Index: 4466836 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8154. Min Range: -10.8154
Max Act: 10.1904. Min Act: -0.1700
Data Index: 1284888 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8154. Min Range: -10.8154
Max Act: 10.1904. Min Act: -0.1700
Data Index: 1538817 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19