Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3114 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3677. Min Range: -8.3677
Max Act: 8.3677. Min Act: -0.1700
Data Index: 7890379 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3677. Min Range: -8.3677
Max Act: 8.3052. Min Act: -0.1700
Data Index: 3398669 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3677. Min Range: -8.3677
Max Act: 8.2427. Min Act: -0.1700
Data Index: 5215296 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3677. Min Range: -8.3677
Max Act: 8.2427. Min Act: -0.1700
Data Index: 2400578 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3677. Min Range: -8.3677
Max Act: 8.1802. Min Act: -0.1696
Data Index: 501565 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3677. Min Range: -8.3677
Max Act: 8.0552. Min Act: -0.1700
Data Index: 6637410 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3677. Min Range: -8.3677
Max Act: 8.0552. Min Act: -0.1700
Data Index: 3416638 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3677. Min Range: -8.3677
Max Act: 8.0552. Min Act: -0.1699
Data Index: 7497991 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3677. Min Range: -8.3677
Max Act: 8.0552. Min Act: -0.1700
Data Index: 7346796 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3677. Min Range: -8.3677
Max Act: 8.0552. Min Act: -0.1700
Data Index: 6518296 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3677. Min Range: -8.3677
Max Act: 7.9927. Min Act: -0.1700
Data Index: 6986218 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3677. Min Range: -8.3677
Max Act: 7.9927. Min Act: -0.1700
Data Index: 7979457 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3677. Min Range: -8.3677
Max Act: 7.8677. Min Act: -0.1700
Data Index: 6348693 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3677. Min Range: -8.3677
Max Act: 7.9302. Min Act: -0.1700
Data Index: 2894614 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3677. Min Range: -8.3677
Max Act: 7.9302. Min Act: -0.1700
Data Index: 6769271 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3677. Min Range: -8.3677
Max Act: 7.8677. Min Act: -0.1700
Data Index: 6574875 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3677. Min Range: -8.3677
Max Act: 7.9302. Min Act: -0.1700
Data Index: 2160992 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3677. Min Range: -8.3677
Max Act: 7.8677. Min Act: -0.1700
Data Index: 2954253 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3677. Min Range: -8.3677
Max Act: 7.8677. Min Act: -0.1700
Data Index: 6348026 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3677. Min Range: -8.3677
Max Act: 7.8677. Min Act: -0.1700
Data Index: 7712872 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19