Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1825 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1778. Min Range: -5.1778
Max Act: 5.1778. Min Act: -0.1700
Data Index: 4438621 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1778. Min Range: -5.1778
Max Act: 4.9903. Min Act: -0.1700
Data Index: 859862 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1778. Min Range: -5.1778
Max Act: 4.8653. Min Act: -0.1700
Data Index: 8739850 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1778. Min Range: -5.1778
Max Act: 4.8340. Min Act: -0.1700
Data Index: 312291 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1778. Min Range: -5.1778
Max Act: 4.7403. Min Act: -0.1700
Data Index: 6475223 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1778. Min Range: -5.1778
Max Act: 4.7403. Min Act: -0.1700
Data Index: 976942 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1778. Min Range: -5.1778
Max Act: 4.7403. Min Act: -0.1700
Data Index: 1368003 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1778. Min Range: -5.1778
Max Act: 4.7090. Min Act: -0.1700
Data Index: 1610002 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1778. Min Range: -5.1778
Max Act: 4.7090. Min Act: -0.1700
Data Index: 419224 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1778. Min Range: -5.1778
Max Act: 4.6465. Min Act: -0.1700
Data Index: 569624 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1778. Min Range: -5.1778
Max Act: 4.7090. Min Act: -0.1700
Data Index: 6126926 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1778. Min Range: -5.1778
Max Act: 4.6778. Min Act: -0.1700
Data Index: 3994617 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1778. Min Range: -5.1778
Max Act: 4.6465. Min Act: -0.1700
Data Index: 6911460 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1778. Min Range: -5.1778
Max Act: 4.6465. Min Act: -0.1700
Data Index: 3965745 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1778. Min Range: -5.1778
Max Act: 4.6153. Min Act: -0.1700
Data Index: 1919985 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1778. Min Range: -5.1778
Max Act: 4.5840. Min Act: -0.1700
Data Index: 4561872 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1778. Min Range: -5.1778
Max Act: 4.5840. Min Act: -0.1700
Data Index: 3711710 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1778. Min Range: -5.1778
Max Act: 4.6153. Min Act: -0.1700
Data Index: 4208249 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1778. Min Range: -5.1778
Max Act: 4.5528. Min Act: -0.1700
Data Index: 5449182 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1778. Min Range: -5.1778
Max Act: 4.5215. Min Act: -0.1700
Data Index: 4813465 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #19