Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5752 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0144. Min Range: -3.0144
Max Act: 3.0144. Min Act: -0.1700
Data Index: 7424904 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0144. Min Range: -3.0144
Max Act: 3.0144. Min Act: -0.1700
Data Index: 3546587 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0144. Min Range: -3.0144
Max Act: 2.9670. Min Act: -0.1700
Data Index: 6758383 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0144. Min Range: -3.0144
Max Act: 2.9511. Min Act: -0.1700
Data Index: 1868715 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0144. Min Range: -3.0144
Max Act: 2.9511. Min Act: -0.1700
Data Index: 4062063 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0144. Min Range: -3.0144
Max Act: 2.9511. Min Act: -0.1700
Data Index: 6858398 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0144. Min Range: -3.0144
Max Act: 2.9511. Min Act: -0.1700
Data Index: 245395 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0144. Min Range: -3.0144
Max Act: 2.9353. Min Act: -0.1700
Data Index: 5989252 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0144. Min Range: -3.0144
Max Act: 2.9353. Min Act: -0.1700
Data Index: 3823865 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0144. Min Range: -3.0144
Max Act: 2.9353. Min Act: -0.1700
Data Index: 4134016 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0144. Min Range: -3.0144
Max Act: 2.9195. Min Act: -0.1700
Data Index: 4126307 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0144. Min Range: -3.0144
Max Act: 2.9036. Min Act: -0.1700
Data Index: 7115464 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0144. Min Range: -3.0144
Max Act: 2.9195. Min Act: -0.1700
Data Index: 6718636 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0144. Min Range: -3.0144
Max Act: 2.8877. Min Act: -0.1700
Data Index: 1334137 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0144. Min Range: -3.0144
Max Act: 2.9036. Min Act: -0.1700
Data Index: 8003753 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0144. Min Range: -3.0144
Max Act: 2.8877. Min Act: -0.1700
Data Index: 6439506 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0144. Min Range: -3.0144
Max Act: 2.8877. Min Act: -0.1700
Data Index: 6293487 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0144. Min Range: -3.0144
Max Act: 2.8877. Min Act: -0.1700
Data Index: 2864019 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0144. Min Range: -3.0144
Max Act: 2.8877. Min Act: -0.1700
Data Index: 2857690 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0144. Min Range: -3.0144
Max Act: 2.9036. Min Act: -0.1700
Data Index: 3508140 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #19