Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4053 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9904. Min Range: -7.9904
Max Act: 7.9904. Min Act: -0.1700
Data Index: 7636747 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9904. Min Range: -7.9904
Max Act: 7.6467. Min Act: -0.1700
Data Index: 4102849 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9904. Min Range: -7.9904
Max Act: 7.6154. Min Act: -0.1700
Data Index: 3954154 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9904. Min Range: -7.9904
Max Act: 7.5217. Min Act: -0.1700
Data Index: 98083 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9904. Min Range: -7.9904
Max Act: 7.4279. Min Act: -0.1700
Data Index: 881198 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9904. Min Range: -7.9904
Max Act: 7.4279. Min Act: -0.1700
Data Index: 5195325 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9904. Min Range: -7.9904
Max Act: 7.4279. Min Act: -0.1700
Data Index: 1449856 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9904. Min Range: -7.9904
Max Act: 7.3967. Min Act: -0.1700
Data Index: 1934269 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9904. Min Range: -7.9904
Max Act: 7.3654. Min Act: -0.1700
Data Index: 6356936 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9904. Min Range: -7.9904
Max Act: 7.3654. Min Act: -0.1700
Data Index: 7053811 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9904. Min Range: -7.9904
Max Act: 7.3654. Min Act: -0.1700
Data Index: 987789 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9904. Min Range: -7.9904
Max Act: 7.3342. Min Act: -0.1700
Data Index: 4474128 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9904. Min Range: -7.9904
Max Act: 7.3029. Min Act: -0.1700
Data Index: 7256857 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9904. Min Range: -7.9904
Max Act: 7.3029. Min Act: -0.1700
Data Index: 450767 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9904. Min Range: -7.9904
Max Act: 7.2717. Min Act: -0.1700
Data Index: 6938307 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9904. Min Range: -7.9904
Max Act: 7.2717. Min Act: -0.1700
Data Index: 6938308 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9904. Min Range: -7.9904
Max Act: 7.2404. Min Act: -0.1700
Data Index: 2460508 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9904. Min Range: -7.9904
Max Act: 7.2404. Min Act: -0.1700
Data Index: 8602500 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9904. Min Range: -7.9904
Max Act: 7.2092. Min Act: -0.1700
Data Index: 8429005 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9904. Min Range: -7.9904
Max Act: 7.2092. Min Act: -0.1700
Data Index: 4898299 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #19