Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3107 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3758. Min Range: -6.3758
Max Act: 6.3758. Min Act: -0.1700
Data Index: 1374384 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3758. Min Range: -6.3758
Max Act: 6.3758. Min Act: -0.1700
Data Index: 6532054 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3758. Min Range: -6.3758
Max Act: 6.3758. Min Act: -0.1700
Data Index: 7672640 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3758. Min Range: -6.3758
Max Act: 6.3446. Min Act: -0.1700
Data Index: 2479433 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3758. Min Range: -6.3758
Max Act: 6.3446. Min Act: -0.1700
Data Index: 5750212 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3758. Min Range: -6.3758
Max Act: 6.3133. Min Act: -0.1700
Data Index: 3626887 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3758. Min Range: -6.3758
Max Act: 6.2821. Min Act: -0.1700
Data Index: 8136071 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3758. Min Range: -6.3758
Max Act: 6.2821. Min Act: -0.1700
Data Index: 5927405 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3758. Min Range: -6.3758
Max Act: 6.2821. Min Act: -0.1700
Data Index: 6628436 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3758. Min Range: -6.3758
Max Act: 6.2821. Min Act: -0.1700
Data Index: 5916176 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3758. Min Range: -6.3758
Max Act: 6.2196. Min Act: -0.1700
Data Index: 7328681 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3758. Min Range: -6.3758
Max Act: 6.2821. Min Act: -0.1700
Data Index: 1469025 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3758. Min Range: -6.3758
Max Act: 6.2508. Min Act: -0.1700
Data Index: 8685985 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3758. Min Range: -6.3758
Max Act: 6.2196. Min Act: -0.1700
Data Index: 1952080 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3758. Min Range: -6.3758
Max Act: 6.2196. Min Act: -0.1700
Data Index: 1601090 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3758. Min Range: -6.3758
Max Act: 6.2196. Min Act: -0.1700
Data Index: 4510945 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3758. Min Range: -6.3758
Max Act: 6.2196. Min Act: -0.1700
Data Index: 547947 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3758. Min Range: -6.3758
Max Act: 6.2196. Min Act: -0.1700
Data Index: 1019984 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3758. Min Range: -6.3758
Max Act: 6.2196. Min Act: -0.1700
Data Index: 1136947 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3758. Min Range: -6.3758
Max Act: 6.2196. Min Act: -0.1700
Data Index: 6037857 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19