Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5274 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.5615. Min Act: -0.1700
Data Index: 2127304 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.3428. Min Act: -0.1700
Data Index: 7949575 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.3115. Min Act: -0.1700
Data Index: 8198003 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.2803. Min Act: -0.1700
Data Index: 3012757 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.3115. Min Act: -0.1700
Data Index: 3005903 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.2178. Min Act: -0.1700
Data Index: 3406292 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.2490. Min Act: -0.1700
Data Index: 7536236 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.1553. Min Act: -0.1700
Data Index: 8349232 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.1553. Min Act: -0.1700
Data Index: 3840934 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.1240. Min Act: -0.1700
Data Index: 2838348 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.0928. Min Act: -0.1700
Data Index: 5697170 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.0928. Min Act: -0.1700
Data Index: 6502237 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.0928. Min Act: -0.1700
Data Index: 8349233 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.0928. Min Act: -0.1700
Data Index: 3406289 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.0303. Min Act: -0.1700
Data Index: 2916429 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.0303. Min Act: -0.1700
Data Index: 8825416 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.0303. Min Act: -0.1700
Data Index: 5544425 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5615. Min Range: -5.5615
Max Act: 4.9990. Min Act: -0.1700
Data Index: 4927609 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5615. Min Range: -5.5615
Max Act: 4.9990. Min Act: -0.1700
Data Index: 8316060 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5615. Min Range: -5.5615
Max Act: 4.9990. Min Act: -0.1700
Data Index: 7421899 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19