Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 525 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0884. Min Range: -8.0884
Max Act: 8.0884. Min Act: -0.1700
Data Index: 8463416 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0884. Min Range: -8.0884
Max Act: 8.0259. Min Act: -0.1700
Data Index: 4804977 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0884. Min Range: -8.0884
Max Act: 8.0259. Min Act: -0.1700
Data Index: 5378626 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0884. Min Range: -8.0884
Max Act: 7.8384. Min Act: -0.1700
Data Index: 2236152 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0884. Min Range: -8.0884
Max Act: 7.7134. Min Act: -0.1700
Data Index: 8463409 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0884. Min Range: -8.0884
Max Act: 7.6197. Min Act: -0.1700
Data Index: 8463414 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0884. Min Range: -8.0884
Max Act: 7.5572. Min Act: -0.1700
Data Index: 7087527 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0884. Min Range: -8.0884
Max Act: 7.5572. Min Act: -0.1700
Data Index: 8463410 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0884. Min Range: -8.0884
Max Act: 7.5572. Min Act: -0.1700
Data Index: 4702660 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0884. Min Range: -8.0884
Max Act: 7.4634. Min Act: -0.1700
Data Index: 8463415 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0884. Min Range: -8.0884
Max Act: 7.4322. Min Act: -0.1700
Data Index: 8463413 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0884. Min Range: -8.0884
Max Act: 7.3697. Min Act: -0.1700
Data Index: 6836628 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0884. Min Range: -8.0884
Max Act: 7.3072. Min Act: -0.1700
Data Index: 8463417 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0884. Min Range: -8.0884
Max Act: 7.3072. Min Act: -0.1700
Data Index: 3131981 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0884. Min Range: -8.0884
Max Act: 7.3072. Min Act: -0.1700
Data Index: 6700534 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0884. Min Range: -8.0884
Max Act: 7.3072. Min Act: -0.1700
Data Index: 8117821 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0884. Min Range: -8.0884
Max Act: 7.2759. Min Act: -0.1700
Data Index: 5287981 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0884. Min Range: -8.0884
Max Act: 7.2759. Min Act: -0.1700
Data Index: 5037635 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0884. Min Range: -8.0884
Max Act: 7.2759. Min Act: -0.1700
Data Index: 4234378 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0884. Min Range: -8.0884
Max Act: 7.2134. Min Act: -0.1700
Data Index: 5731640 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19