Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3552 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.7247. Min Act: -0.1700
Data Index: 6495732 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.7247. Min Act: -0.1700
Data Index: 3318354 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.3809. Min Act: -0.1700
Data Index: 4847527 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.2872. Min Act: -0.1700
Data Index: 1244048 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.2247. Min Act: -0.1700
Data Index: 8730177 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.1934. Min Act: -0.1700
Data Index: 1539042 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.1934. Min Act: -0.1700
Data Index: 2337224 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.1622. Min Act: -0.1700
Data Index: 4445435 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.1309. Min Act: -0.1700
Data Index: 2930272 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.1309. Min Act: -0.1700
Data Index: 2139515 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.0997. Min Act: -0.1700
Data Index: 854882 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.1309. Min Act: -0.1700
Data Index: 3215519 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.0997. Min Act: -0.1700
Data Index: 4186887 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.0684. Min Act: -0.1700
Data Index: 6108536 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.0059. Min Act: -0.1700
Data Index: 7510077 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.0372. Min Act: -0.1700
Data Index: 2181557 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.0372. Min Act: -0.1700
Data Index: 6290908 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.0372. Min Act: -0.1700
Data Index: 1093816 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.0372. Min Act: -0.1700
Data Index: 6939612 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.0059. Min Act: -0.1700
Data Index: 6634919 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19