Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4777 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7703. Min Range: -5.7703
Max Act: 5.7703. Min Act: -0.1700
Data Index: 3505070 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7703. Min Range: -5.7703
Max Act: 5.5516. Min Act: -0.1700
Data Index: 3418961 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7703. Min Range: -5.7703
Max Act: 5.5516. Min Act: -0.1700
Data Index: 4170167 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7703. Min Range: -5.7703
Max Act: 5.5203. Min Act: -0.1700
Data Index: 659700 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7703. Min Range: -5.7703
Max Act: 5.5203. Min Act: -0.1700
Data Index: 4820945 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7703. Min Range: -5.7703
Max Act: 5.4578. Min Act: -0.1700
Data Index: 8604625 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7703. Min Range: -5.7703
Max Act: 5.4266. Min Act: -0.1700
Data Index: 7441484 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7703. Min Range: -5.7703
Max Act: 5.3953. Min Act: -0.1700
Data Index: 1542899 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7703. Min Range: -5.7703
Max Act: 5.3953. Min Act: -0.1700
Data Index: 7843558 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7703. Min Range: -5.7703
Max Act: 5.3641. Min Act: -0.1700
Data Index: 5997365 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7703. Min Range: -5.7703
Max Act: 5.3641. Min Act: -0.1700
Data Index: 1011732 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7703. Min Range: -5.7703
Max Act: 5.3328. Min Act: -0.1700
Data Index: 2148487 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7703. Min Range: -5.7703
Max Act: 5.3016. Min Act: -0.1700
Data Index: 1764816 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7703. Min Range: -5.7703
Max Act: 5.3328. Min Act: -0.1700
Data Index: 7357945 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7703. Min Range: -5.7703
Max Act: 5.3016. Min Act: -0.1700
Data Index: 1559974 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7703. Min Range: -5.7703
Max Act: 5.2703. Min Act: -0.1700
Data Index: 2682760 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7703. Min Range: -5.7703
Max Act: 5.2703. Min Act: -0.1700
Data Index: 4684413 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7703. Min Range: -5.7703
Max Act: 5.2703. Min Act: -0.1700
Data Index: 5646757 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7703. Min Range: -5.7703
Max Act: 5.2703. Min Act: -0.1700
Data Index: 5282644 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7703. Min Range: -5.7703
Max Act: 5.2078. Min Act: -0.1700
Data Index: 2054350 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #19