Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3870 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9464. Min Range: -5.9464
Max Act: 5.9464. Min Act: -0.1700
Data Index: 3770666 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9464. Min Range: -5.9464
Max Act: 5.8527. Min Act: -0.1700
Data Index: 8469872 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9464. Min Range: -5.9464
Max Act: 5.7277. Min Act: -0.1700
Data Index: 7710934 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9464. Min Range: -5.9464
Max Act: 5.5402. Min Act: -0.1700
Data Index: 7240337 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9464. Min Range: -5.9464
Max Act: 5.5402. Min Act: -0.1700
Data Index: 2216980 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9464. Min Range: -5.9464
Max Act: 5.4464. Min Act: -0.1700
Data Index: 2702754 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9464. Min Range: -5.9464
Max Act: 5.3527. Min Act: -0.1700
Data Index: 1674415 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9464. Min Range: -5.9464
Max Act: 5.3527. Min Act: -0.1700
Data Index: 5018747 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9464. Min Range: -5.9464
Max Act: 5.3839. Min Act: -0.1700
Data Index: 8469871 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9464. Min Range: -5.9464
Max Act: 5.3214. Min Act: -0.1700
Data Index: 6069636 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9464. Min Range: -5.9464
Max Act: 5.2589. Min Act: -0.1700
Data Index: 5709753 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9464. Min Range: -5.9464
Max Act: 5.2902. Min Act: -0.1700
Data Index: 2146617 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9464. Min Range: -5.9464
Max Act: 5.2589. Min Act: -0.1700
Data Index: 2040723 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9464. Min Range: -5.9464
Max Act: 5.2589. Min Act: -0.1700
Data Index: 6397326 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9464. Min Range: -5.9464
Max Act: 5.2589. Min Act: -0.1700
Data Index: 3481830 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9464. Min Range: -5.9464
Max Act: 5.2277. Min Act: -0.1700
Data Index: 872399 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9464. Min Range: -5.9464
Max Act: 5.2277. Min Act: -0.1700
Data Index: 6772297 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9464. Min Range: -5.9464
Max Act: 5.2277. Min Act: -0.1700
Data Index: 1523602 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9464. Min Range: -5.9464
Max Act: 5.2277. Min Act: -0.1700
Data Index: 3904693 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9464. Min Range: -5.9464
Max Act: 5.2277. Min Act: -0.1700
Data Index: 5705249 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19