Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1713 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2887. Min Range: -8.2887
Max Act: 8.2887. Min Act: -0.1700
Data Index: 5885719 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2887. Min Range: -8.2887
Max Act: 8.0387. Min Act: -0.1700
Data Index: 917291 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2887. Min Range: -8.2887
Max Act: 7.9137. Min Act: -0.1700
Data Index: 4479245 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2887. Min Range: -8.2887
Max Act: 7.9137. Min Act: -0.1700
Data Index: 1309031 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2887. Min Range: -8.2887
Max Act: 7.9137. Min Act: -0.1700
Data Index: 4208665 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2887. Min Range: -8.2887
Max Act: 7.8824. Min Act: -0.1700
Data Index: 975591 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2887. Min Range: -8.2887
Max Act: 7.8199. Min Act: -0.1700
Data Index: 5832592 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2887. Min Range: -8.2887
Max Act: 7.7574. Min Act: -0.1700
Data Index: 1894014 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2887. Min Range: -8.2887
Max Act: 7.7887. Min Act: -0.1700
Data Index: 8094741 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2887. Min Range: -8.2887
Max Act: 7.7887. Min Act: -0.1700
Data Index: 6672130 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2887. Min Range: -8.2887
Max Act: 7.7262. Min Act: -0.1700
Data Index: 7930713 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2887. Min Range: -8.2887
Max Act: 7.6637. Min Act: -0.1700
Data Index: 7080080 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2887. Min Range: -8.2887
Max Act: 7.5699. Min Act: -0.1700
Data Index: 555999 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2887. Min Range: -8.2887
Max Act: 7.5699. Min Act: -0.1700
Data Index: 5579549 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2887. Min Range: -8.2887
Max Act: 7.5387. Min Act: -0.1700
Data Index: 1789801 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2887. Min Range: -8.2887
Max Act: 7.5074. Min Act: -0.1700
Data Index: 2165699 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2887. Min Range: -8.2887
Max Act: 7.5074. Min Act: -0.1700
Data Index: 5269198 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2887. Min Range: -8.2887
Max Act: 7.4762. Min Act: -0.1700
Data Index: 1707118 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2887. Min Range: -8.2887
Max Act: 7.5074. Min Act: -0.1700
Data Index: 2602490 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2887. Min Range: -8.2887
Max Act: 7.5074. Min Act: -0.1700
Data Index: 8408318 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19