Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5555 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1987. Min Range: -7.1987
Max Act: 7.1987. Min Act: -0.1700
Data Index: 5517821 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1987. Min Range: -7.1987
Max Act: 6.4487. Min Act: -0.1700
Data Index: 8784710 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1987. Min Range: -7.1987
Max Act: 6.4175. Min Act: -0.1700
Data Index: 6200206 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1987. Min Range: -7.1987
Max Act: 6.4175. Min Act: -0.1700
Data Index: 5347609 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1987. Min Range: -7.1987
Max Act: 6.3550. Min Act: -0.1700
Data Index: 2613767 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1987. Min Range: -7.1987
Max Act: 6.3550. Min Act: -0.1700
Data Index: 7625375 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1987. Min Range: -7.1987
Max Act: 6.3550. Min Act: -0.1700
Data Index: 1897497 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1987. Min Range: -7.1987
Max Act: 6.3237. Min Act: -0.1700
Data Index: 6370105 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1987. Min Range: -7.1987
Max Act: 6.2925. Min Act: -0.1700
Data Index: 6190323 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1987. Min Range: -7.1987
Max Act: 6.2925. Min Act: -0.1700
Data Index: 4156154 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1987. Min Range: -7.1987
Max Act: 6.2925. Min Act: -0.1700
Data Index: 906848 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1987. Min Range: -7.1987
Max Act: 6.2300. Min Act: -0.1700
Data Index: 6775182 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1987. Min Range: -7.1987
Max Act: 6.2300. Min Act: -0.1700
Data Index: 8753947 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1987. Min Range: -7.1987
Max Act: 6.1987. Min Act: -0.1700
Data Index: 3143823 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1987. Min Range: -7.1987
Max Act: 6.1987. Min Act: -0.1700
Data Index: 2334707 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1987. Min Range: -7.1987
Max Act: 6.1987. Min Act: -0.1700
Data Index: 6270911 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1987. Min Range: -7.1987
Max Act: 6.1675. Min Act: -0.1700
Data Index: 3306676 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1987. Min Range: -7.1987
Max Act: 6.1362. Min Act: -0.1700
Data Index: 5459605 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1987. Min Range: -7.1987
Max Act: 6.1050. Min Act: -0.1700
Data Index: 4531054 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1987. Min Range: -7.1987
Max Act: 6.1362. Min Act: -0.1700
Data Index: 3847377 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19