Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3315 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3262. Min Range: -5.3262
Max Act: 5.3262. Min Act: -0.1700
Data Index: 7813804 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3262. Min Range: -5.3262
Max Act: 5.0449. Min Act: -0.1700
Data Index: 1993994 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3262. Min Range: -5.3262
Max Act: 4.9824. Min Act: -0.1700
Data Index: 1742131 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3262. Min Range: -5.3262
Max Act: 4.9512. Min Act: -0.1700
Data Index: 8783805 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3262. Min Range: -5.3262
Max Act: 4.8887. Min Act: -0.1700
Data Index: 6032294 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3262. Min Range: -5.3262
Max Act: 4.8887. Min Act: -0.1700
Data Index: 6795296 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3262. Min Range: -5.3262
Max Act: 4.8574. Min Act: -0.1700
Data Index: 4098436 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3262. Min Range: -5.3262
Max Act: 4.8574. Min Act: -0.1700
Data Index: 3751817 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3262. Min Range: -5.3262
Max Act: 4.8262. Min Act: -0.1700
Data Index: 223294 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3262. Min Range: -5.3262
Max Act: 4.8262. Min Act: -0.1700
Data Index: 2277652 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3262. Min Range: -5.3262
Max Act: 4.8262. Min Act: -0.1700
Data Index: 8707277 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3262. Min Range: -5.3262
Max Act: 4.7949. Min Act: -0.1700
Data Index: 6093129 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3262. Min Range: -5.3262
Max Act: 4.7637. Min Act: -0.1700
Data Index: 5568667 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3262. Min Range: -5.3262
Max Act: 4.7324. Min Act: -0.1700
Data Index: 271122 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3262. Min Range: -5.3262
Max Act: 4.7324. Min Act: -0.1700
Data Index: 241524 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3262. Min Range: -5.3262
Max Act: 4.7324. Min Act: -0.1700
Data Index: 8162923 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3262. Min Range: -5.3262
Max Act: 4.7012. Min Act: -0.1700
Data Index: 1762461 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3262. Min Range: -5.3262
Max Act: 4.6699. Min Act: -0.1700
Data Index: 7136499 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3262. Min Range: -5.3262
Max Act: 4.6387. Min Act: -0.1700
Data Index: 2796624 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3262. Min Range: -5.3262
Max Act: 4.6387. Min Act: -0.1700
Data Index: 1109540 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19