Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4273 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6887. Min Range: -5.6887
Max Act: 5.6887. Min Act: -0.1700
Data Index: 2244952 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6887. Min Range: -5.6887
Max Act: 5.6887. Min Act: -0.1700
Data Index: 3095841 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6887. Min Range: -5.6887
Max Act: 5.6262. Min Act: -0.1700
Data Index: 564366 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6887. Min Range: -5.6887
Max Act: 5.5012. Min Act: -0.1700
Data Index: 6794794 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6887. Min Range: -5.6887
Max Act: 5.5012. Min Act: -0.1700
Data Index: 5481641 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6887. Min Range: -5.6887
Max Act: 5.4700. Min Act: -0.1700
Data Index: 4474717 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6887. Min Range: -5.6887
Max Act: 5.4700. Min Act: -0.1700
Data Index: 8722624 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6887. Min Range: -5.6887
Max Act: 5.4700. Min Act: -0.1700
Data Index: 8579622 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6887. Min Range: -5.6887
Max Act: 5.4387. Min Act: -0.1700
Data Index: 4501785 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6887. Min Range: -5.6887
Max Act: 5.4075. Min Act: -0.1700
Data Index: 8819408 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6887. Min Range: -5.6887
Max Act: 5.4075. Min Act: -0.1700
Data Index: 70976 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6887. Min Range: -5.6887
Max Act: 5.4075. Min Act: -0.1700
Data Index: 1901438 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6887. Min Range: -5.6887
Max Act: 5.3450. Min Act: -0.1700
Data Index: 5328845 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6887. Min Range: -5.6887
Max Act: 5.3762. Min Act: -0.1700
Data Index: 6457282 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6887. Min Range: -5.6887
Max Act: 5.3450. Min Act: -0.1700
Data Index: 3190121 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6887. Min Range: -5.6887
Max Act: 5.3137. Min Act: -0.1700
Data Index: 8535471 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6887. Min Range: -5.6887
Max Act: 5.3137. Min Act: -0.1700
Data Index: 1971787 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6887. Min Range: -5.6887
Max Act: 5.3137. Min Act: -0.1700
Data Index: 7564106 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6887. Min Range: -5.6887
Max Act: 5.3137. Min Act: -0.1700
Data Index: 554334 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6887. Min Range: -5.6887
Max Act: 5.2825. Min Act: -0.1700
Data Index: 2317745 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #19