Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4923 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5635. Min Range: -6.5635
Max Act: 6.5635. Min Act: -0.1700
Data Index: 5252243 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5635. Min Range: -6.5635
Max Act: 6.0010. Min Act: -0.1700
Data Index: 8043491 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5635. Min Range: -6.5635
Max Act: 5.9697. Min Act: -0.1700
Data Index: 173600 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5635. Min Range: -6.5635
Max Act: 5.9697. Min Act: -0.1700
Data Index: 4386776 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5635. Min Range: -6.5635
Max Act: 5.9385. Min Act: -0.1700
Data Index: 8313063 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5635. Min Range: -6.5635
Max Act: 5.9072. Min Act: -0.1700
Data Index: 8197821 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5635. Min Range: -6.5635
Max Act: 5.8760. Min Act: -0.1700
Data Index: 8153931 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5635. Min Range: -6.5635
Max Act: 5.8447. Min Act: -0.1700
Data Index: 4993741 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5635. Min Range: -6.5635
Max Act: 5.8447. Min Act: -0.1700
Data Index: 3132320 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5635. Min Range: -6.5635
Max Act: 5.8760. Min Act: -0.1700
Data Index: 5282064 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5635. Min Range: -6.5635
Max Act: 5.8135. Min Act: -0.1700
Data Index: 4056209 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5635. Min Range: -6.5635
Max Act: 5.7510. Min Act: -0.1700
Data Index: 4636889 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5635. Min Range: -6.5635
Max Act: 5.7510. Min Act: -0.1700
Data Index: 3847124 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5635. Min Range: -6.5635
Max Act: 5.7197. Min Act: -0.1700
Data Index: 7893384 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5635. Min Range: -6.5635
Max Act: 5.6572. Min Act: -0.1700
Data Index: 2076000 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5635. Min Range: -6.5635
Max Act: 5.6260. Min Act: -0.1700
Data Index: 482957 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5635. Min Range: -6.5635
Max Act: 5.5322. Min Act: -0.1700
Data Index: 5254658 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5635. Min Range: -6.5635
Max Act: 5.5635. Min Act: -0.1700
Data Index: 2544253 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5635. Min Range: -6.5635
Max Act: 5.5322. Min Act: -0.1700
Data Index: 41029 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5635. Min Range: -6.5635
Max Act: 5.5010. Min Act: -0.1700
Data Index: 8197606 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #19