Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2829 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0137. Min Range: -6.0137
Max Act: 6.0137. Min Act: -0.1700
Data Index: 522614 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0137. Min Range: -6.0137
Max Act: 5.9512. Min Act: -0.1700
Data Index: 2302902 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0137. Min Range: -6.0137
Max Act: 5.9825. Min Act: -0.1700
Data Index: 6042801 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0137. Min Range: -6.0137
Max Act: 5.9512. Min Act: -0.1700
Data Index: 5922076 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0137. Min Range: -6.0137
Max Act: 5.8887. Min Act: -0.1700
Data Index: 3041945 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0137. Min Range: -6.0137
Max Act: 5.8575. Min Act: -0.1700
Data Index: 4852984 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0137. Min Range: -6.0137
Max Act: 5.8887. Min Act: -0.1700
Data Index: 1105732 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0137. Min Range: -6.0137
Max Act: 5.8575. Min Act: -0.1700
Data Index: 8773874 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0137. Min Range: -6.0137
Max Act: 5.8575. Min Act: -0.1700
Data Index: 5484305 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0137. Min Range: -6.0137
Max Act: 5.8575. Min Act: -0.1700
Data Index: 8654013 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0137. Min Range: -6.0137
Max Act: 5.8262. Min Act: -0.1700
Data Index: 1131282 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0137. Min Range: -6.0137
Max Act: 5.8262. Min Act: -0.1700
Data Index: 1900998 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0137. Min Range: -6.0137
Max Act: 5.8262. Min Act: -0.1700
Data Index: 4495891 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0137. Min Range: -6.0137
Max Act: 5.8262. Min Act: -0.1700
Data Index: 7921939 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0137. Min Range: -6.0137
Max Act: 5.7950. Min Act: -0.1700
Data Index: 5123610 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0137. Min Range: -6.0137
Max Act: 5.8262. Min Act: -0.1700
Data Index: 4412353 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0137. Min Range: -6.0137
Max Act: 5.7950. Min Act: -0.1700
Data Index: 4252441 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0137. Min Range: -6.0137
Max Act: 5.7637. Min Act: -0.1700
Data Index: 1473812 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0137. Min Range: -6.0137
Max Act: 5.7637. Min Act: -0.1700
Data Index: 5960127 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0137. Min Range: -6.0137
Max Act: 5.7637. Min Act: -0.1700
Data Index: 1952557 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19