Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1148 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3725. Min Range: -7.3725
Max Act: 7.3725. Min Act: -0.1700
Data Index: 8664053 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3725. Min Range: -7.3725
Max Act: 7.1225. Min Act: -0.1700
Data Index: 4152156 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3725. Min Range: -7.3725
Max Act: 7.0913. Min Act: -0.1700
Data Index: 5570034 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3725. Min Range: -7.3725
Max Act: 7.0600. Min Act: -0.1700
Data Index: 1226422 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3725. Min Range: -7.3725
Max Act: 6.9038. Min Act: -0.1700
Data Index: 370490 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3725. Min Range: -7.3725
Max Act: 6.9350. Min Act: -0.1700
Data Index: 4745892 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3725. Min Range: -7.3725
Max Act: 6.9038. Min Act: -0.1700
Data Index: 1524849 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3725. Min Range: -7.3725
Max Act: 6.9038. Min Act: -0.1700
Data Index: 7269457 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3725. Min Range: -7.3725
Max Act: 6.9350. Min Act: -0.1700
Data Index: 7140762 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3725. Min Range: -7.3725
Max Act: 6.9038. Min Act: -0.1700
Data Index: 1894653 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3725. Min Range: -7.3725
Max Act: 6.9038. Min Act: -0.1700
Data Index: 900754 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3725. Min Range: -7.3725
Max Act: 6.9038. Min Act: -0.1700
Data Index: 2714690 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3725. Min Range: -7.3725
Max Act: 6.8725. Min Act: -0.1700
Data Index: 7305679 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3725. Min Range: -7.3725
Max Act: 6.8725. Min Act: -0.1700
Data Index: 5996633 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3725. Min Range: -7.3725
Max Act: 6.8725. Min Act: -0.1700
Data Index: 4152631 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3725. Min Range: -7.3725
Max Act: 6.8413. Min Act: -0.1700
Data Index: 1730945 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3725. Min Range: -7.3725
Max Act: 6.8413. Min Act: -0.1700
Data Index: 2749249 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3725. Min Range: -7.3725
Max Act: 6.8100. Min Act: -0.1700
Data Index: 1620671 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3725. Min Range: -7.3725
Max Act: 6.8100. Min Act: -0.1700
Data Index: 8560270 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3725. Min Range: -7.3725
Max Act: 6.7788. Min Act: -0.1700
Data Index: 3041595 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #19