Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1959 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4074. Min Range: -9.4074
Max Act: 9.4074. Min Act: -0.1700
Data Index: 5475318 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4074. Min Range: -9.4074
Max Act: 9.3449. Min Act: -0.1700
Data Index: 4543714 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4074. Min Range: -9.4074
Max Act: 9.2199. Min Act: -0.1700
Data Index: 6389109 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4074. Min Range: -9.4074
Max Act: 9.2199. Min Act: -0.1700
Data Index: 1317225 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4074. Min Range: -9.4074
Max Act: 9.2199. Min Act: -0.1700
Data Index: 5509607 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4074. Min Range: -9.4074
Max Act: 9.0949. Min Act: -0.1700
Data Index: 8330911 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4074. Min Range: -9.4074
Max Act: 9.0949. Min Act: -0.1700
Data Index: 5403626 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4074. Min Range: -9.4074
Max Act: 8.9699. Min Act: -0.1700
Data Index: 635479 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4074. Min Range: -9.4074
Max Act: 9.0324. Min Act: -0.1700
Data Index: 5903863 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4074. Min Range: -9.4074
Max Act: 9.0324. Min Act: -0.1700
Data Index: 4502073 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4074. Min Range: -9.4074
Max Act: 8.9699. Min Act: -0.1700
Data Index: 8113026 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4074. Min Range: -9.4074
Max Act: 8.9699. Min Act: -0.1700
Data Index: 8438601 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4074. Min Range: -9.4074
Max Act: 8.9699. Min Act: -0.1700
Data Index: 1114125 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4074. Min Range: -9.4074
Max Act: 8.9699. Min Act: -0.1700
Data Index: 2489048 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4074. Min Range: -9.4074
Max Act: 8.9074. Min Act: -0.1700
Data Index: 856963 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4074. Min Range: -9.4074
Max Act: 8.8449. Min Act: -0.1700
Data Index: 1625941 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4074. Min Range: -9.4074
Max Act: 8.9074. Min Act: -0.1700
Data Index: 60865 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4074. Min Range: -9.4074
Max Act: 8.8449. Min Act: -0.1700
Data Index: 667500 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4074. Min Range: -9.4074
Max Act: 8.8449. Min Act: -0.1700
Data Index: 5916466 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4074. Min Range: -9.4074
Max Act: 8.8449. Min Act: -0.1700
Data Index: 769331 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19