Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3591 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6812. Min Range: -4.6812
Max Act: 4.6812. Min Act: -0.1700
Data Index: 6225308 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6812. Min Range: -4.6812
Max Act: 4.5875. Min Act: -0.1700
Data Index: 5643789 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6812. Min Range: -4.6812
Max Act: 4.5562. Min Act: -0.1700
Data Index: 7067499 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6812. Min Range: -4.6812
Max Act: 4.5250. Min Act: -0.1700
Data Index: 1448212 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6812. Min Range: -4.6812
Max Act: 4.5250. Min Act: -0.1700
Data Index: 8350431 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6812. Min Range: -4.6812
Max Act: 4.4937. Min Act: -0.1700
Data Index: 1510211 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6812. Min Range: -4.6812
Max Act: 4.4937. Min Act: -0.1700
Data Index: 879602 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6812. Min Range: -4.6812
Max Act: 4.4625. Min Act: -0.1700
Data Index: 5997346 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6812. Min Range: -4.6812
Max Act: 4.4625. Min Act: -0.1700
Data Index: 1834639 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6812. Min Range: -4.6812
Max Act: 4.4937. Min Act: -0.1700
Data Index: 6385079 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6812. Min Range: -4.6812
Max Act: 4.4000. Min Act: -0.1700
Data Index: 7428427 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6812. Min Range: -4.6812
Max Act: 4.4312. Min Act: -0.1700
Data Index: 6513749 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6812. Min Range: -4.6812
Max Act: 4.4312. Min Act: -0.1700
Data Index: 3729783 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6812. Min Range: -4.6812
Max Act: 4.4312. Min Act: -0.1700
Data Index: 3244058 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6812. Min Range: -4.6812
Max Act: 4.4312. Min Act: -0.1697
Data Index: 6995283 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6812. Min Range: -4.6812
Max Act: 4.4312. Min Act: -0.1700
Data Index: 5832476 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6812. Min Range: -4.6812
Max Act: 4.4000. Min Act: -0.1700
Data Index: 6491674 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6812. Min Range: -4.6812
Max Act: 4.4000. Min Act: -0.1700
Data Index: 8286243 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6812. Min Range: -4.6812
Max Act: 4.4000. Min Act: -0.1700
Data Index: 1685160 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6812. Min Range: -4.6812
Max Act: 4.4000. Min Act: -0.1700
Data Index: 4561085 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #19