Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1528 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5574. Min Range: -7.5574
Max Act: 7.5574. Min Act: -0.1700
Data Index: 5135798 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5574. Min Range: -7.5574
Max Act: 7.4636. Min Act: -0.1700
Data Index: 4030232 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5574. Min Range: -7.5574
Max Act: 7.3074. Min Act: -0.1700
Data Index: 3896941 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5574. Min Range: -7.5574
Max Act: 7.2136. Min Act: -0.1700
Data Index: 7764188 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5574. Min Range: -7.5574
Max Act: 7.1511. Min Act: -0.1700
Data Index: 7273425 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5574. Min Range: -7.5574
Max Act: 7.1824. Min Act: -0.1700
Data Index: 7534585 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5574. Min Range: -7.5574
Max Act: 7.1511. Min Act: -0.1700
Data Index: 826779 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5574. Min Range: -7.5574
Max Act: 7.0886. Min Act: -0.1700
Data Index: 4775871 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5574. Min Range: -7.5574
Max Act: 7.0886. Min Act: -0.1700
Data Index: 1353176 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5574. Min Range: -7.5574
Max Act: 7.1199. Min Act: -0.1700
Data Index: 400350 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5574. Min Range: -7.5574
Max Act: 7.1199. Min Act: -0.1700
Data Index: 7870375 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5574. Min Range: -7.5574
Max Act: 7.0574. Min Act: -0.1700
Data Index: 8100372 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5574. Min Range: -7.5574
Max Act: 7.0886. Min Act: -0.1700
Data Index: 4239953 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5574. Min Range: -7.5574
Max Act: 7.0261. Min Act: -0.1700
Data Index: 4206616 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5574. Min Range: -7.5574
Max Act: 6.9949. Min Act: -0.1700
Data Index: 4380666 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5574. Min Range: -7.5574
Max Act: 7.0261. Min Act: -0.1700
Data Index: 5194526 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5574. Min Range: -7.5574
Max Act: 7.0261. Min Act: -0.1700
Data Index: 750757 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5574. Min Range: -7.5574
Max Act: 7.0261. Min Act: -0.1700
Data Index: 1243122 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5574. Min Range: -7.5574
Max Act: 6.9949. Min Act: -0.1700
Data Index: 3230974 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5574. Min Range: -7.5574
Max Act: 6.9949. Min Act: -0.1700
Data Index: 5049279 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19