Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2311 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5029. Min Range: -8.5029
Max Act: 8.5029. Min Act: -0.1700
Data Index: 3528680 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5029. Min Range: -8.5029
Max Act: 8.3154. Min Act: -0.1700
Data Index: 8609634 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5029. Min Range: -8.5029
Max Act: 8.2529. Min Act: -0.1700
Data Index: 6059614 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5029. Min Range: -8.5029
Max Act: 8.0029. Min Act: -0.1700
Data Index: 2331242 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5029. Min Range: -8.5029
Max Act: 8.0029. Min Act: -0.1700
Data Index: 159680 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5029. Min Range: -8.5029
Max Act: 8.0654. Min Act: -0.1700
Data Index: 129532 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5029. Min Range: -8.5029
Max Act: 8.0029. Min Act: -0.1700
Data Index: 1696223 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5029. Min Range: -8.5029
Max Act: 7.9404. Min Act: -0.1700
Data Index: 4965906 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5029. Min Range: -8.5029
Max Act: 7.8779. Min Act: -0.1700
Data Index: 6426517 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5029. Min Range: -8.5029
Max Act: 7.8779. Min Act: -0.1700
Data Index: 774587 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5029. Min Range: -8.5029
Max Act: 7.8779. Min Act: -0.1700
Data Index: 75151 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5029. Min Range: -8.5029
Max Act: 7.8779. Min Act: -0.1700
Data Index: 4591611 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5029. Min Range: -8.5029
Max Act: 7.8154. Min Act: -0.1700
Data Index: 196298 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5029. Min Range: -8.5029
Max Act: 7.8154. Min Act: -0.1700
Data Index: 4063268 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5029. Min Range: -8.5029
Max Act: 7.8154. Min Act: -0.1700
Data Index: 2974601 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5029. Min Range: -8.5029
Max Act: 7.8154. Min Act: -0.1700
Data Index: 1180803 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5029. Min Range: -8.5029
Max Act: 7.7841. Min Act: -0.1700
Data Index: 6285904 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5029. Min Range: -8.5029
Max Act: 7.7841. Min Act: -0.1700
Data Index: 685177 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5029. Min Range: -8.5029
Max Act: 7.7529. Min Act: -0.1700
Data Index: 5487185 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5029. Min Range: -8.5029
Max Act: 7.7529. Min Act: -0.1700
Data Index: 1702095 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19