Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4270 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1450. Min Range: -5.1450
Max Act: 5.1450. Min Act: -0.1700
Data Index: 2821479 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1450. Min Range: -5.1450
Max Act: 5.0512. Min Act: -0.1700
Data Index: 5944510 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1450. Min Range: -5.1450
Max Act: 5.0512. Min Act: -0.1700
Data Index: 4847354 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1450. Min Range: -5.1450
Max Act: 5.0200. Min Act: -0.1700
Data Index: 8717379 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1450. Min Range: -5.1450
Max Act: 5.0200. Min Act: -0.1700
Data Index: 7352468 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1450. Min Range: -5.1450
Max Act: 4.9887. Min Act: -0.1700
Data Index: 8591659 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1450. Min Range: -5.1450
Max Act: 4.9887. Min Act: -0.1700
Data Index: 4831114 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1450. Min Range: -5.1450
Max Act: 4.9575. Min Act: -0.1700
Data Index: 3098386 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1450. Min Range: -5.1450
Max Act: 4.9262. Min Act: -0.1698
Data Index: 7528834 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1450. Min Range: -5.1450
Max Act: 4.8950. Min Act: -0.1700
Data Index: 7948686 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1450. Min Range: -5.1450
Max Act: 4.8950. Min Act: -0.1700
Data Index: 6580921 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1450. Min Range: -5.1450
Max Act: 4.8950. Min Act: -0.1700
Data Index: 7881494 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1450. Min Range: -5.1450
Max Act: 4.8325. Min Act: -0.1700
Data Index: 6070891 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1450. Min Range: -5.1450
Max Act: 4.8012. Min Act: -0.1700
Data Index: 3727877 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1450. Min Range: -5.1450
Max Act: 4.8012. Min Act: -0.1700
Data Index: 7227433 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1450. Min Range: -5.1450
Max Act: 4.7387. Min Act: -0.1700
Data Index: 4307064 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1450. Min Range: -5.1450
Max Act: 4.7387. Min Act: -0.1700
Data Index: 7106601 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1450. Min Range: -5.1450
Max Act: 4.7387. Min Act: -0.1700
Data Index: 5015247 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1450. Min Range: -5.1450
Max Act: 4.7387. Min Act: -0.1700
Data Index: 6845081 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1450. Min Range: -5.1450
Max Act: 4.7387. Min Act: -0.1700
Data Index: 7394467 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19