Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3390 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0720. Min Range: -7.0720
Max Act: 7.0720. Min Act: -0.1700
Data Index: 849932 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0720. Min Range: -7.0720
Max Act: 7.0408. Min Act: -0.1700
Data Index: 4992287 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0720. Min Range: -7.0720
Max Act: 6.9470. Min Act: -0.1700
Data Index: 8732378 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0720. Min Range: -7.0720
Max Act: 6.9158. Min Act: -0.1700
Data Index: 7254789 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0720. Min Range: -7.0720
Max Act: 6.9158. Min Act: -0.1700
Data Index: 3916977 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0720. Min Range: -7.0720
Max Act: 6.9158. Min Act: -0.1700
Data Index: 4812455 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0720. Min Range: -7.0720
Max Act: 6.8845. Min Act: -0.1700
Data Index: 5165671 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0720. Min Range: -7.0720
Max Act: 6.8845. Min Act: -0.1700
Data Index: 6921733 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0720. Min Range: -7.0720
Max Act: 6.8845. Min Act: -0.1700
Data Index: 348665 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0720. Min Range: -7.0720
Max Act: 6.8533. Min Act: -0.1700
Data Index: 1655704 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0720. Min Range: -7.0720
Max Act: 6.8533. Min Act: -0.1700
Data Index: 5165672 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0720. Min Range: -7.0720
Max Act: 6.8533. Min Act: -0.1700
Data Index: 1322702 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0720. Min Range: -7.0720
Max Act: 6.8220. Min Act: -0.1700
Data Index: 613545 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0720. Min Range: -7.0720
Max Act: 6.7908. Min Act: -0.1700
Data Index: 4651947 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0720. Min Range: -7.0720
Max Act: 6.7908. Min Act: -0.1700
Data Index: 429961 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0720. Min Range: -7.0720
Max Act: 6.7908. Min Act: -0.1700
Data Index: 6821472 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0720. Min Range: -7.0720
Max Act: 6.7908. Min Act: -0.1700
Data Index: 2305037 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0720. Min Range: -7.0720
Max Act: 6.7283. Min Act: -0.1700
Data Index: 1199234 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0720. Min Range: -7.0720
Max Act: 6.7595. Min Act: -0.1700
Data Index: 4342409 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0720. Min Range: -7.0720
Max Act: 6.7595. Min Act: -0.1700
Data Index: 7343673 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19