Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3012 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3902. Min Range: -5.3902
Max Act: 5.3902. Min Act: -0.1700
Data Index: 3053716 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3902. Min Range: -5.3902
Max Act: 5.3590. Min Act: -0.1700
Data Index: 2829479 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3902. Min Range: -5.3902
Max Act: 5.2652. Min Act: -0.1700
Data Index: 6879114 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3902. Min Range: -5.3902
Max Act: 5.2340. Min Act: -0.1700
Data Index: 1571471 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3902. Min Range: -5.3902
Max Act: 5.1715. Min Act: -0.1700
Data Index: 2225672 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3902. Min Range: -5.3902
Max Act: 5.1402. Min Act: -0.1700
Data Index: 5606734 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3902. Min Range: -5.3902
Max Act: 5.1402. Min Act: -0.1700
Data Index: 6183809 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3902. Min Range: -5.3902
Max Act: 5.1090. Min Act: -0.1700
Data Index: 6472825 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3902. Min Range: -5.3902
Max Act: 5.1090. Min Act: -0.1700
Data Index: 3342087 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3902. Min Range: -5.3902
Max Act: 5.1090. Min Act: -0.1700
Data Index: 2223420 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3902. Min Range: -5.3902
Max Act: 5.0777. Min Act: -0.1700
Data Index: 124952 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3902. Min Range: -5.3902
Max Act: 5.0777. Min Act: -0.1700
Data Index: 1419705 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3902. Min Range: -5.3902
Max Act: 5.1090. Min Act: -0.1700
Data Index: 3802806 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3902. Min Range: -5.3902
Max Act: 5.0152. Min Act: -0.1700
Data Index: 241970 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3902. Min Range: -5.3902
Max Act: 5.0152. Min Act: -0.1700
Data Index: 4659727 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3902. Min Range: -5.3902
Max Act: 5.0152. Min Act: -0.1700
Data Index: 8805668 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3902. Min Range: -5.3902
Max Act: 5.0152. Min Act: -0.1700
Data Index: 3274402 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3902. Min Range: -5.3902
Max Act: 4.9840. Min Act: -0.1700
Data Index: 2671457 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3902. Min Range: -5.3902
Max Act: 5.0152. Min Act: -0.1700
Data Index: 3037842 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3902. Min Range: -5.3902
Max Act: 4.9840. Min Act: -0.1700
Data Index: 3101661 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #19