Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 483 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4885. Min Range: -8.4885
Max Act: 8.3635. Min Act: -0.1700
Data Index: 1170153 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4885. Min Range: -8.4885
Max Act: 8.4885. Min Act: -0.1700
Data Index: 2468176 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4885. Min Range: -8.4885
Max Act: 8.0510. Min Act: -0.1700
Data Index: 3385018 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4885. Min Range: -8.4885
Max Act: 7.9885. Min Act: -0.1700
Data Index: 7281543 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4885. Min Range: -8.4885
Max Act: 7.8010. Min Act: -0.1700
Data Index: 6725798 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4885. Min Range: -8.4885
Max Act: 7.8010. Min Act: -0.1700
Data Index: 3635874 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4885. Min Range: -8.4885
Max Act: 7.8010. Min Act: -0.1700
Data Index: 4469214 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4885. Min Range: -8.4885
Max Act: 7.7385. Min Act: -0.1700
Data Index: 2520331 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4885. Min Range: -8.4885
Max Act: 7.7385. Min Act: -0.1700
Data Index: 4438473 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4885. Min Range: -8.4885
Max Act: 7.7385. Min Act: -0.1700
Data Index: 3481477 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4885. Min Range: -8.4885
Max Act: 7.7385. Min Act: -0.1700
Data Index: 5404339 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4885. Min Range: -8.4885
Max Act: 7.6760. Min Act: -0.1700
Data Index: 4156974 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4885. Min Range: -8.4885
Max Act: 7.6760. Min Act: -0.1700
Data Index: 5568069 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4885. Min Range: -8.4885
Max Act: 7.6760. Min Act: -0.1700
Data Index: 8047557 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4885. Min Range: -8.4885
Max Act: 7.6135. Min Act: -0.1700
Data Index: 3940547 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4885. Min Range: -8.4885
Max Act: 7.6135. Min Act: -0.1700
Data Index: 7972254 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4885. Min Range: -8.4885
Max Act: 7.6135. Min Act: -0.1700
Data Index: 6874009 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4885. Min Range: -8.4885
Max Act: 7.6135. Min Act: -0.1700
Data Index: 3134260 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4885. Min Range: -8.4885
Max Act: 7.5510. Min Act: -0.1700
Data Index: 2926925 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4885. Min Range: -8.4885
Max Act: 7.5510. Min Act: -0.1700
Data Index: 8077974 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19