Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4932 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3497. Min Range: -5.3497
Max Act: 5.3497. Min Act: -0.1700
Data Index: 3670293 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3497. Min Range: -5.3497
Max Act: 5.2559. Min Act: -0.1700
Data Index: 985194 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3497. Min Range: -5.3497
Max Act: 5.1934. Min Act: -0.1700
Data Index: 7556843 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3497. Min Range: -5.3497
Max Act: 5.0997. Min Act: -0.1700
Data Index: 6871917 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3497. Min Range: -5.3497
Max Act: 5.0997. Min Act: -0.1700
Data Index: 3575714 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3497. Min Range: -5.3497
Max Act: 4.9747. Min Act: -0.1700
Data Index: 5242330 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3497. Min Range: -5.3497
Max Act: 4.9434. Min Act: -0.1700
Data Index: 3975790 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3497. Min Range: -5.3497
Max Act: 4.9122. Min Act: -0.1700
Data Index: 735994 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3497. Min Range: -5.3497
Max Act: 4.9122. Min Act: -0.1700
Data Index: 4307165 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3497. Min Range: -5.3497
Max Act: 4.8809. Min Act: -0.1700
Data Index: 7121935 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3497. Min Range: -5.3497
Max Act: 4.8809. Min Act: -0.1700
Data Index: 4227812 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3497. Min Range: -5.3497
Max Act: 4.8497. Min Act: -0.1700
Data Index: 4205498 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3497. Min Range: -5.3497
Max Act: 4.8184. Min Act: -0.1700
Data Index: 842464 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3497. Min Range: -5.3497
Max Act: 4.8497. Min Act: -0.1700
Data Index: 2470263 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3497. Min Range: -5.3497
Max Act: 4.8497. Min Act: -0.1700
Data Index: 4307164 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3497. Min Range: -5.3497
Max Act: 4.8184. Min Act: -0.1700
Data Index: 2583145 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3497. Min Range: -5.3497
Max Act: 4.8184. Min Act: -0.1700
Data Index: 6157848 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3497. Min Range: -5.3497
Max Act: 4.7559. Min Act: -0.1700
Data Index: 8002814 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3497. Min Range: -5.3497
Max Act: 4.7872. Min Act: -0.1700
Data Index: 2548141 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3497. Min Range: -5.3497
Max Act: 4.7247. Min Act: -0.1700
Data Index: 5012834 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #19