Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4707 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3645. Min Range: -3.3645
Max Act: 3.3645. Min Act: -0.1700
Data Index: 345023 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3645. Min Range: -3.3645
Max Act: 3.2860. Min Act: -0.1700
Data Index: 1825064 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3645. Min Range: -3.3645
Max Act: 3.0815. Min Act: -0.1700
Data Index: 7381483 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3645. Min Range: -3.3645
Max Act: 2.9551. Min Act: -0.1700
Data Index: 5947707 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3645. Min Range: -3.3645
Max Act: 2.9551. Min Act: -0.1700
Data Index: 6698993 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3645. Min Range: -3.3645
Max Act: 2.9393. Min Act: -0.1700
Data Index: 2698894 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3645. Min Range: -3.3645
Max Act: 2.9551. Min Act: -0.1700
Data Index: 659291 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3645. Min Range: -3.3645
Max Act: 2.9393. Min Act: -0.1700
Data Index: 5305264 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3645. Min Range: -3.3645
Max Act: 2.9393. Min Act: -0.1700
Data Index: 1816707 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3645. Min Range: -3.3645
Max Act: 2.9235. Min Act: -0.1700
Data Index: 4749582 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3645. Min Range: -3.3645
Max Act: 2.9076. Min Act: -0.1700
Data Index: 2475131 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3645. Min Range: -3.3645
Max Act: 2.8918. Min Act: -0.1700
Data Index: 7441797 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3645. Min Range: -3.3645
Max Act: 2.9076. Min Act: -0.1700
Data Index: 818462 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3645. Min Range: -3.3645
Max Act: 2.8918. Min Act: -0.1700
Data Index: 7111775 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3645. Min Range: -3.3645
Max Act: 2.8759. Min Act: -0.1700
Data Index: 4545600 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3645. Min Range: -3.3645
Max Act: 2.8600. Min Act: -0.1700
Data Index: 613626 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3645. Min Range: -3.3645
Max Act: 2.8759. Min Act: -0.1700
Data Index: 954673 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3645. Min Range: -3.3645
Max Act: 2.8759. Min Act: -0.1700
Data Index: 4419317 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3645. Min Range: -3.3645
Max Act: 2.8441. Min Act: -0.1700
Data Index: 6885385 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3645. Min Range: -3.3645
Max Act: 2.8600. Min Act: -0.1700
Data Index: 4884331 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19