Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3950 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7574. Min Range: -8.7574
Max Act: 8.7574. Min Act: -0.1700
Data Index: 5869968 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7574. Min Range: -8.7574
Max Act: 8.1949. Min Act: -0.1700
Data Index: 6443000 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7574. Min Range: -8.7574
Max Act: 8.1949. Min Act: -0.1700
Data Index: 3387248 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7574. Min Range: -8.7574
Max Act: 8.0699. Min Act: -0.1700
Data Index: 5602235 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7574. Min Range: -8.7574
Max Act: 8.0074. Min Act: -0.1700
Data Index: 8826111 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7574. Min Range: -8.7574
Max Act: 8.0074. Min Act: -0.1700
Data Index: 2465584 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7574. Min Range: -8.7574
Max Act: 8.0074. Min Act: -0.1700
Data Index: 1547641 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7574. Min Range: -8.7574
Max Act: 8.0074. Min Act: -0.1700
Data Index: 927323 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7574. Min Range: -8.7574
Max Act: 8.0074. Min Act: -0.1700
Data Index: 7227351 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7574. Min Range: -8.7574
Max Act: 7.9449. Min Act: -0.1700
Data Index: 7359903 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7574. Min Range: -8.7574
Max Act: 7.9137. Min Act: -0.1700
Data Index: 7153588 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7574. Min Range: -8.7574
Max Act: 8.0074. Min Act: -0.1700
Data Index: 3998079 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7574. Min Range: -8.7574
Max Act: 7.9137. Min Act: -0.1700
Data Index: 4664942 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7574. Min Range: -8.7574
Max Act: 7.8824. Min Act: -0.1700
Data Index: 448742 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7574. Min Range: -8.7574
Max Act: 7.8824. Min Act: -0.1700
Data Index: 2460529 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7574. Min Range: -8.7574
Max Act: 7.8512. Min Act: -0.1700
Data Index: 4885095 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7574. Min Range: -8.7574
Max Act: 7.8512. Min Act: -0.1700
Data Index: 1615090 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7574. Min Range: -8.7574
Max Act: 7.8199. Min Act: -0.1700
Data Index: 8333763 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7574. Min Range: -8.7574
Max Act: 7.8199. Min Act: -0.1700
Data Index: 522532 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7574. Min Range: -8.7574
Max Act: 7.8199. Min Act: -0.1700
Data Index: 6597944 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19