Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2559 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.5884. Min Act: -0.1700
Data Index: 231476 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.5884. Min Act: -0.1700
Data Index: 7521929 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.5572. Min Act: -0.1700
Data Index: 2702747 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.4947. Min Act: -0.1700
Data Index: 8374769 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.4634. Min Act: -0.1700
Data Index: 5570142 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.4634. Min Act: -0.1700
Data Index: 886208 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.4322. Min Act: -0.1700
Data Index: 3321072 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.4009. Min Act: -0.1700
Data Index: 1003724 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.4009. Min Act: -0.1700
Data Index: 3230713 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.4009. Min Act: -0.1700
Data Index: 5693789 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.3384. Min Act: -0.1700
Data Index: 4490039 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.3072. Min Act: -0.1700
Data Index: 3871679 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.3384. Min Act: -0.1700
Data Index: 7160743 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.3697. Min Act: -0.1700
Data Index: 7903263 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.3072. Min Act: -0.1700
Data Index: 1133130 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.2759. Min Act: -0.1700
Data Index: 2702756 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.2447. Min Act: -0.1700
Data Index: 4253464 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.2447. Min Act: -0.1700
Data Index: 7959456 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.2447. Min Act: -0.1700
Data Index: 1688422 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.2447. Min Act: -0.1700
Data Index: 462740 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #19