Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4184 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6575. Min Range: -7.6575
Max Act: 7.6575. Min Act: -0.1700
Data Index: 7216113 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6575. Min Range: -7.6575
Max Act: 7.3450. Min Act: -0.1700
Data Index: 93226 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6575. Min Range: -7.6575
Max Act: 7.2825. Min Act: -0.1700
Data Index: 4705640 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6575. Min Range: -7.6575
Max Act: 7.2200. Min Act: -0.1700
Data Index: 3906697 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6575. Min Range: -7.6575
Max Act: 7.2200. Min Act: -0.1700
Data Index: 8811925 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6575. Min Range: -7.6575
Max Act: 7.1887. Min Act: -0.1700
Data Index: 662416 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6575. Min Range: -7.6575
Max Act: 7.1575. Min Act: -0.1700
Data Index: 8829211 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6575. Min Range: -7.6575
Max Act: 7.1575. Min Act: -0.1700
Data Index: 2762583 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6575. Min Range: -7.6575
Max Act: 7.1262. Min Act: -0.1700
Data Index: 866699 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6575. Min Range: -7.6575
Max Act: 7.0950. Min Act: -0.1700
Data Index: 4561491 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6575. Min Range: -7.6575
Max Act: 7.0637. Min Act: -0.1700
Data Index: 405384 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6575. Min Range: -7.6575
Max Act: 7.0950. Min Act: -0.1700
Data Index: 3670597 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6575. Min Range: -7.6575
Max Act: 7.0950. Min Act: -0.1700
Data Index: 8813621 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6575. Min Range: -7.6575
Max Act: 7.0637. Min Act: -0.1700
Data Index: 6613447 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6575. Min Range: -7.6575
Max Act: 7.0637. Min Act: -0.1700
Data Index: 6613439 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6575. Min Range: -7.6575
Max Act: 7.0325. Min Act: -0.1700
Data Index: 3345462 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6575. Min Range: -7.6575
Max Act: 7.0012. Min Act: -0.1700
Data Index: 7455104 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6575. Min Range: -7.6575
Max Act: 7.0012. Min Act: -0.1700
Data Index: 4480943 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6575. Min Range: -7.6575
Max Act: 6.9700. Min Act: -0.1700
Data Index: 8417131 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6575. Min Range: -7.6575
Max Act: 6.9700. Min Act: -0.1700
Data Index: 6702385 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19