Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4620 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3851. Min Range: -8.3851
Max Act: 8.3851. Min Act: -0.1700
Data Index: 1685636 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3851. Min Range: -8.3851
Max Act: 7.9163. Min Act: -0.1700
Data Index: 2254355 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3851. Min Range: -8.3851
Max Act: 7.9163. Min Act: -0.1700
Data Index: 4683395 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3851. Min Range: -8.3851
Max Act: 7.8538. Min Act: -0.1700
Data Index: 2223019 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3851. Min Range: -8.3851
Max Act: 7.7601. Min Act: -0.1700
Data Index: 6435551 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3851. Min Range: -8.3851
Max Act: 7.7601. Min Act: -0.1700
Data Index: 76948 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3851. Min Range: -8.3851
Max Act: 7.7288. Min Act: -0.1700
Data Index: 5162395 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3851. Min Range: -8.3851
Max Act: 7.6976. Min Act: -0.1700
Data Index: 3717140 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3851. Min Range: -8.3851
Max Act: 7.6663. Min Act: -0.1700
Data Index: 429289 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3851. Min Range: -8.3851
Max Act: 7.6351. Min Act: -0.1700
Data Index: 7156851 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3851. Min Range: -8.3851
Max Act: 7.6038. Min Act: -0.1700
Data Index: 3970938 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3851. Min Range: -8.3851
Max Act: 7.6038. Min Act: -0.1700
Data Index: 6666829 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3851. Min Range: -8.3851
Max Act: 7.6038. Min Act: -0.1700
Data Index: 677839 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3851. Min Range: -8.3851
Max Act: 7.6038. Min Act: -0.1700
Data Index: 7297304 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3851. Min Range: -8.3851
Max Act: 7.6038. Min Act: -0.1700
Data Index: 137366 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3851. Min Range: -8.3851
Max Act: 7.5726. Min Act: -0.1700
Data Index: 618553 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3851. Min Range: -8.3851
Max Act: 7.5413. Min Act: -0.1700
Data Index: 662273 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3851. Min Range: -8.3851
Max Act: 7.5413. Min Act: -0.1700
Data Index: 1219704 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3851. Min Range: -8.3851
Max Act: 7.4788. Min Act: -0.1700
Data Index: 879097 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3851. Min Range: -8.3851
Max Act: 7.5101. Min Act: -0.1700
Data Index: 4081637 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19