Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5065 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0395. Min Range: -7.0395
Max Act: 7.0395. Min Act: -0.1700
Data Index: 4719042 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0395. Min Range: -7.0395
Max Act: 7.0083. Min Act: -0.1700
Data Index: 5861881 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0395. Min Range: -7.0395
Max Act: 6.9770. Min Act: -0.1700
Data Index: 7924333 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0395. Min Range: -7.0395
Max Act: 6.8520. Min Act: -0.1700
Data Index: 4889814 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0395. Min Range: -7.0395
Max Act: 6.7895. Min Act: -0.1700
Data Index: 4748999 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0395. Min Range: -7.0395
Max Act: 6.7895. Min Act: -0.1700
Data Index: 3570431 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0395. Min Range: -7.0395
Max Act: 6.7270. Min Act: -0.1700
Data Index: 8271433 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0395. Min Range: -7.0395
Max Act: 6.6333. Min Act: -0.1700
Data Index: 2537827 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0395. Min Range: -7.0395
Max Act: 6.6020. Min Act: -0.1700
Data Index: 5978890 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0395. Min Range: -7.0395
Max Act: 6.5708. Min Act: -0.1700
Data Index: 6782945 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0395. Min Range: -7.0395
Max Act: 6.5395. Min Act: -0.1700
Data Index: 522705 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0395. Min Range: -7.0395
Max Act: 6.5083. Min Act: -0.1700
Data Index: 4886929 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0395. Min Range: -7.0395
Max Act: 6.5083. Min Act: -0.1700
Data Index: 5244265 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0395. Min Range: -7.0395
Max Act: 6.5083. Min Act: -0.1700
Data Index: 5504668 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0395. Min Range: -7.0395
Max Act: 6.5395. Min Act: -0.1700
Data Index: 6978767 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0395. Min Range: -7.0395
Max Act: 6.4770. Min Act: -0.1700
Data Index: 1276863 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0395. Min Range: -7.0395
Max Act: 6.5083. Min Act: -0.1700
Data Index: 1430932 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0395. Min Range: -7.0395
Max Act: 6.4770. Min Act: -0.1700
Data Index: 5359782 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0395. Min Range: -7.0395
Max Act: 6.5083. Min Act: -0.1700
Data Index: 251073 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0395. Min Range: -7.0395
Max Act: 6.4770. Min Act: -0.1700
Data Index: 3575865 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #19