Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3691 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2988. Min Range: -8.2988
Max Act: 8.2988. Min Act: -0.1700
Data Index: 630882 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2988. Min Range: -8.2988
Max Act: 8.1113. Min Act: -0.1700
Data Index: 7589343 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2988. Min Range: -8.2988
Max Act: 8.0488. Min Act: -0.1700
Data Index: 5433313 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2988. Min Range: -8.2988
Max Act: 7.9863. Min Act: -0.1700
Data Index: 2268663 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2988. Min Range: -8.2988
Max Act: 7.9238. Min Act: -0.1700
Data Index: 3180395 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2988. Min Range: -8.2988
Max Act: 7.9238. Min Act: -0.1700
Data Index: 1870489 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2988. Min Range: -8.2988
Max Act: 7.8613. Min Act: -0.1700
Data Index: 8766392 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2988. Min Range: -8.2988
Max Act: 7.8613. Min Act: -0.1700
Data Index: 6503077 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2988. Min Range: -8.2988
Max Act: 7.8613. Min Act: -0.1700
Data Index: 5331189 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2988. Min Range: -8.2988
Max Act: 7.8613. Min Act: -0.1700
Data Index: 8063517 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2988. Min Range: -8.2988
Max Act: 7.7988. Min Act: -0.1700
Data Index: 4952564 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2988. Min Range: -8.2988
Max Act: 7.7988. Min Act: -0.1700
Data Index: 2239923 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2988. Min Range: -8.2988
Max Act: 7.7988. Min Act: -0.1700
Data Index: 2768223 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2988. Min Range: -8.2988
Max Act: 7.6738. Min Act: -0.1700
Data Index: 6305440 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2988. Min Range: -8.2988
Max Act: 7.7363. Min Act: -0.1700
Data Index: 6070573 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2988. Min Range: -8.2988
Max Act: 7.6738. Min Act: -0.1700
Data Index: 6407015 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2988. Min Range: -8.2988
Max Act: 7.6738. Min Act: -0.1700
Data Index: 3571584 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2988. Min Range: -8.2988
Max Act: 7.7363. Min Act: -0.1700
Data Index: 4835834 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2988. Min Range: -8.2988
Max Act: 7.6738. Min Act: -0.1700
Data Index: 2182352 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2988. Min Range: -8.2988
Max Act: 7.6738. Min Act: -0.1700
Data Index: 5363017 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #19