Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2814 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2944. Min Range: -8.2944
Max Act: 8.2944. Min Act: -0.1700
Data Index: 4425940 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2944. Min Range: -8.2944
Max Act: 8.1382. Min Act: -0.1700
Data Index: 4674993 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2944. Min Range: -8.2944
Max Act: 8.1069. Min Act: -0.1700
Data Index: 8038086 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2944. Min Range: -8.2944
Max Act: 7.9819. Min Act: -0.1700
Data Index: 7183460 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2944. Min Range: -8.2944
Max Act: 7.9507. Min Act: -0.1700
Data Index: 129962 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2944. Min Range: -8.2944
Max Act: 7.9194. Min Act: -0.1700
Data Index: 2922454 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2944. Min Range: -8.2944
Max Act: 7.8882. Min Act: -0.1700
Data Index: 6255614 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2944. Min Range: -8.2944
Max Act: 7.9194. Min Act: -0.1700
Data Index: 8756186 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2944. Min Range: -8.2944
Max Act: 7.8882. Min Act: -0.1700
Data Index: 2850293 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2944. Min Range: -8.2944
Max Act: 7.8569. Min Act: -0.1700
Data Index: 7777891 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2944. Min Range: -8.2944
Max Act: 7.8257. Min Act: -0.1700
Data Index: 4457510 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2944. Min Range: -8.2944
Max Act: 7.7632. Min Act: -0.1700
Data Index: 8507946 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2944. Min Range: -8.2944
Max Act: 7.7007. Min Act: -0.1700
Data Index: 6395089 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2944. Min Range: -8.2944
Max Act: 7.6694. Min Act: -0.1700
Data Index: 4457508 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2944. Min Range: -8.2944
Max Act: 7.6069. Min Act: -0.1700
Data Index: 7273071 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2944. Min Range: -8.2944
Max Act: 7.5757. Min Act: -0.1700
Data Index: 5486928 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2944. Min Range: -8.2944
Max Act: 7.5444. Min Act: -0.1700
Data Index: 3032074 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2944. Min Range: -8.2944
Max Act: 7.5757. Min Act: -0.1700
Data Index: 7623020 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2944. Min Range: -8.2944
Max Act: 7.5757. Min Act: -0.1700
Data Index: 4415939 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2944. Min Range: -8.2944
Max Act: 7.5444. Min Act: -0.1700
Data Index: 245092 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #19