Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3626 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2595. Min Range: -5.2595
Max Act: 5.2595. Min Act: -0.1700
Data Index: 3340287 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2595. Min Range: -5.2595
Max Act: 5.1970. Min Act: -0.1700
Data Index: 1229837 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2595. Min Range: -5.2595
Max Act: 5.1657. Min Act: -0.1700
Data Index: 8526135 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2595. Min Range: -5.2595
Max Act: 5.1345. Min Act: -0.1700
Data Index: 2510961 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2595. Min Range: -5.2595
Max Act: 5.1032. Min Act: -0.1700
Data Index: 3908590 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2595. Min Range: -5.2595
Max Act: 5.1345. Min Act: -0.1700
Data Index: 156010 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2595. Min Range: -5.2595
Max Act: 5.1032. Min Act: -0.1700
Data Index: 2550151 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2595. Min Range: -5.2595
Max Act: 5.0720. Min Act: -0.1700
Data Index: 1968863 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2595. Min Range: -5.2595
Max Act: 5.0407. Min Act: -0.1700
Data Index: 4323204 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2595. Min Range: -5.2595
Max Act: 5.0407. Min Act: -0.1700
Data Index: 600138 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2595. Min Range: -5.2595
Max Act: 5.0720. Min Act: -0.1700
Data Index: 1006127 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2595. Min Range: -5.2595
Max Act: 5.0095. Min Act: -0.1700
Data Index: 372493 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2595. Min Range: -5.2595
Max Act: 4.9470. Min Act: -0.1700
Data Index: 6710580 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2595. Min Range: -5.2595
Max Act: 4.9782. Min Act: -0.1700
Data Index: 6688084 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2595. Min Range: -5.2595
Max Act: 5.0095. Min Act: -0.1700
Data Index: 5475514 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2595. Min Range: -5.2595
Max Act: 4.9470. Min Act: -0.1700
Data Index: 2618930 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2595. Min Range: -5.2595
Max Act: 4.9782. Min Act: -0.1700
Data Index: 3201789 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2595. Min Range: -5.2595
Max Act: 4.9157. Min Act: -0.1700
Data Index: 2472481 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2595. Min Range: -5.2595
Max Act: 4.9157. Min Act: -0.1700
Data Index: 2026489 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2595. Min Range: -5.2595
Max Act: 4.8845. Min Act: -0.1700
Data Index: 976142 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19