Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2257 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5947. Min Range: -8.5947
Max Act: 8.5947. Min Act: -0.1700
Data Index: 2750136 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5947. Min Range: -8.5947
Max Act: 8.2822. Min Act: -0.1700
Data Index: 7152472 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5947. Min Range: -8.5947
Max Act: 8.2822. Min Act: -0.1700
Data Index: 362317 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5947. Min Range: -8.5947
Max Act: 8.1572. Min Act: -0.1700
Data Index: 3443677 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5947. Min Range: -8.5947
Max Act: 8.0322. Min Act: -0.1700
Data Index: 6612900 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5947. Min Range: -8.5947
Max Act: 7.9697. Min Act: -0.1700
Data Index: 5641374 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5947. Min Range: -8.5947
Max Act: 7.9697. Min Act: -0.1700
Data Index: 5444970 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5947. Min Range: -8.5947
Max Act: 7.9697. Min Act: -0.1700
Data Index: 8030364 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5947. Min Range: -8.5947
Max Act: 7.9072. Min Act: -0.1700
Data Index: 1459123 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5947. Min Range: -8.5947
Max Act: 7.9072. Min Act: -0.1700
Data Index: 3294113 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5947. Min Range: -8.5947
Max Act: 7.9072. Min Act: -0.1700
Data Index: 3928985 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5947. Min Range: -8.5947
Max Act: 7.9697. Min Act: -0.1700
Data Index: 6225265 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5947. Min Range: -8.5947
Max Act: 7.8447. Min Act: -0.1700
Data Index: 2055859 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5947. Min Range: -8.5947
Max Act: 7.8447. Min Act: -0.1700
Data Index: 4112570 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5947. Min Range: -8.5947
Max Act: 7.8447. Min Act: -0.1700
Data Index: 97407 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5947. Min Range: -8.5947
Max Act: 7.8447. Min Act: -0.1700
Data Index: 5697012 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5947. Min Range: -8.5947
Max Act: 7.8447. Min Act: -0.1700
Data Index: 6896865 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5947. Min Range: -8.5947
Max Act: 7.7822. Min Act: -0.1700
Data Index: 3118827 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5947. Min Range: -8.5947
Max Act: 7.7822. Min Act: -0.1700
Data Index: 6036155 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5947. Min Range: -8.5947
Max Act: 7.7822. Min Act: -0.1700
Data Index: 5983047 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19