Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2485 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.5615. Min Act: -0.1700
Data Index: 2006148 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.5303. Min Act: -0.1700
Data Index: 4522208 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.4990. Min Act: -0.1700
Data Index: 7999101 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.4678. Min Act: -0.1700
Data Index: 4975554 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.4053. Min Act: -0.1700
Data Index: 5632718 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.3740. Min Act: -0.1700
Data Index: 7940781 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.4053. Min Act: -0.1700
Data Index: 3268171 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.3428. Min Act: -0.1700
Data Index: 6744196 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.3115. Min Act: -0.1700
Data Index: 3626817 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.3740. Min Act: -0.1700
Data Index: 4283932 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.3115. Min Act: -0.1700
Data Index: 1048070 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.3115. Min Act: -0.1700
Data Index: 5702998 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.2803. Min Act: -0.1700
Data Index: 4973681 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.2803. Min Act: -0.1700
Data Index: 7904856 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.3115. Min Act: -0.1700
Data Index: 548888 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.2178. Min Act: -0.1700
Data Index: 2808233 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.3115. Min Act: -0.1700
Data Index: 5510901 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.2803. Min Act: -0.1700
Data Index: 2288805 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.3115. Min Act: -0.1700
Data Index: 6299856 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.2490. Min Act: -0.1700
Data Index: 3844540 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #19