Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6382 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2766. Min Range: -4.2766
Max Act: 4.2766. Min Act: -0.1700
Data Index: 7681244 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2766. Min Range: -4.2766
Max Act: 4.2454. Min Act: -0.1700
Data Index: 2374095 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2766. Min Range: -4.2766
Max Act: 4.2141. Min Act: -0.1700
Data Index: 3900384 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2766. Min Range: -4.2766
Max Act: 4.2141. Min Act: -0.1700
Data Index: 5399514 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2766. Min Range: -4.2766
Max Act: 4.1829. Min Act: -0.1700
Data Index: 112783 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2766. Min Range: -4.2766
Max Act: 4.1829. Min Act: -0.1700
Data Index: 7726632 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2766. Min Range: -4.2766
Max Act: 4.1516. Min Act: -0.1700
Data Index: 2993107 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2766. Min Range: -4.2766
Max Act: 4.1204. Min Act: -0.1700
Data Index: 2776944 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2766. Min Range: -4.2766
Max Act: 4.1204. Min Act: -0.1700
Data Index: 442340 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2766. Min Range: -4.2766
Max Act: 4.1204. Min Act: -0.1700
Data Index: 6746603 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2766. Min Range: -4.2766
Max Act: 4.1204. Min Act: -0.1700
Data Index: 1725160 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2766. Min Range: -4.2766
Max Act: 4.1204. Min Act: -0.1700
Data Index: 4163731 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2766. Min Range: -4.2766
Max Act: 4.0891. Min Act: -0.1700
Data Index: 1724675 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2766. Min Range: -4.2766
Max Act: 4.0891. Min Act: -0.1700
Data Index: 7207635 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2766. Min Range: -4.2766
Max Act: 4.0579. Min Act: -0.1700
Data Index: 5577124 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2766. Min Range: -4.2766
Max Act: 4.0266. Min Act: -0.1700
Data Index: 113873 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2766. Min Range: -4.2766
Max Act: 4.0266. Min Act: -0.1700
Data Index: 6976943 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2766. Min Range: -4.2766
Max Act: 4.0266. Min Act: -0.1700
Data Index: 2230340 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2766. Min Range: -4.2766
Max Act: 3.9953. Min Act: -0.1700
Data Index: 4123889 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2766. Min Range: -4.2766
Max Act: 3.9953. Min Act: -0.1700
Data Index: 3040780 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #19