Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3508 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.9105. Min Act: -0.1700
Data Index: 3094455 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.8792. Min Act: -0.1700
Data Index: 1374062 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.8480. Min Act: -0.1700
Data Index: 2044153 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.8480. Min Act: -0.1700
Data Index: 5973155 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.8480. Min Act: -0.1700
Data Index: 8578470 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.7542. Min Act: -0.1700
Data Index: 5197968 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.7230. Min Act: -0.1700
Data Index: 2208020 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.7542. Min Act: -0.1700
Data Index: 1590287 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.6917. Min Act: -0.1700
Data Index: 7036904 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.6917. Min Act: -0.1700
Data Index: 2274910 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.6605. Min Act: -0.1700
Data Index: 5805419 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.6605. Min Act: -0.1700
Data Index: 2253532 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.6605. Min Act: -0.1700
Data Index: 8117494 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.6605. Min Act: -0.1700
Data Index: 8512871 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.6605. Min Act: -0.1700
Data Index: 6883738 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.6605. Min Act: -0.1700
Data Index: 5962602 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.6292. Min Act: -0.1700
Data Index: 4679511 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.6292. Min Act: -0.1700
Data Index: 1322442 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.6292. Min Act: -0.1700
Data Index: 7730707 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9105. Min Range: -6.9105
Max Act: 6.6292. Min Act: -0.1700
Data Index: 8594507 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19