Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4115 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8463. Min Range: -4.8463
Max Act: 4.8463. Min Act: -0.1700
Data Index: 1592320 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8463. Min Range: -4.8463
Max Act: 4.7526. Min Act: -0.1700
Data Index: 5799761 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8463. Min Range: -4.8463
Max Act: 4.5651. Min Act: -0.1700
Data Index: 2697156 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8463. Min Range: -4.8463
Max Act: 4.5963. Min Act: -0.1700
Data Index: 5986988 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8463. Min Range: -4.8463
Max Act: 4.5026. Min Act: -0.1700
Data Index: 1706393 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8463. Min Range: -4.8463
Max Act: 4.5338. Min Act: -0.1700
Data Index: 6510877 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8463. Min Range: -4.8463
Max Act: 4.5338. Min Act: -0.1700
Data Index: 2725576 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8463. Min Range: -4.8463
Max Act: 4.5338. Min Act: -0.1700
Data Index: 5994671 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8463. Min Range: -4.8463
Max Act: 4.4713. Min Act: -0.1700
Data Index: 4246096 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8463. Min Range: -4.8463
Max Act: 4.4713. Min Act: -0.1700
Data Index: 515181 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8463. Min Range: -4.8463
Max Act: 4.4713. Min Act: -0.1700
Data Index: 346385 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8463. Min Range: -4.8463
Max Act: 4.4713. Min Act: -0.1700
Data Index: 2386686 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8463. Min Range: -4.8463
Max Act: 4.4713. Min Act: -0.1700
Data Index: 1142960 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8463. Min Range: -4.8463
Max Act: 4.4088. Min Act: -0.1700
Data Index: 696467 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8463. Min Range: -4.8463
Max Act: 4.4088. Min Act: -0.1700
Data Index: 5551545 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8463. Min Range: -4.8463
Max Act: 4.3776. Min Act: -0.1700
Data Index: 8267421 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8463. Min Range: -4.8463
Max Act: 4.3776. Min Act: -0.1700
Data Index: 4595754 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8463. Min Range: -4.8463
Max Act: 4.3776. Min Act: -0.1700
Data Index: 6881372 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8463. Min Range: -4.8463
Max Act: 4.3463. Min Act: -0.1700
Data Index: 350780 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8463. Min Range: -4.8463
Max Act: 4.3463. Min Act: -0.1700
Data Index: 2092287 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19