Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4362 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8858. Min Range: -5.8858
Max Act: 5.8858. Min Act: -0.1700
Data Index: 1255679 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8858. Min Range: -5.8858
Max Act: 5.8233. Min Act: -0.1700
Data Index: 4430116 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8858. Min Range: -5.8858
Max Act: 5.7608. Min Act: -0.1700
Data Index: 7216747 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8858. Min Range: -5.8858
Max Act: 5.4795. Min Act: -0.1700
Data Index: 1124353 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8858. Min Range: -5.8858
Max Act: 5.4170. Min Act: -0.1700
Data Index: 5022466 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8858. Min Range: -5.8858
Max Act: 5.4170. Min Act: -0.1700
Data Index: 5333447 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8858. Min Range: -5.8858
Max Act: 5.4170. Min Act: -0.1700
Data Index: 7240546 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8858. Min Range: -5.8858
Max Act: 5.3858. Min Act: -0.1700
Data Index: 7132396 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8858. Min Range: -5.8858
Max Act: 5.3545. Min Act: -0.1700
Data Index: 7258467 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8858. Min Range: -5.8858
Max Act: 5.3233. Min Act: -0.1700
Data Index: 7700925 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8858. Min Range: -5.8858
Max Act: 5.3233. Min Act: -0.1700
Data Index: 3500319 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8858. Min Range: -5.8858
Max Act: 5.2608. Min Act: -0.1700
Data Index: 4316920 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8858. Min Range: -5.8858
Max Act: 5.3233. Min Act: -0.1700
Data Index: 7589503 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8858. Min Range: -5.8858
Max Act: 5.2608. Min Act: -0.1700
Data Index: 6310209 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8858. Min Range: -5.8858
Max Act: 5.2608. Min Act: -0.1700
Data Index: 721504 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8858. Min Range: -5.8858
Max Act: 5.2608. Min Act: -0.1700
Data Index: 3234110 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8858. Min Range: -5.8858
Max Act: 5.2608. Min Act: -0.1700
Data Index: 4746008 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8858. Min Range: -5.8858
Max Act: 5.2608. Min Act: -0.1700
Data Index: 696104 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8858. Min Range: -5.8858
Max Act: 5.2608. Min Act: -0.1700
Data Index: 7180532 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8858. Min Range: -5.8858
Max Act: 5.1983. Min Act: -0.1700
Data Index: 7090837 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19