Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2979 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8321. Min Range: -2.8321
Max Act: 2.8321. Min Act: -0.1700
Data Index: 855537 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8321. Min Range: -2.8321
Max Act: 2.8003. Min Act: -0.1700
Data Index: 1243683 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8321. Min Range: -2.8321
Max Act: 2.8003. Min Act: -0.1700
Data Index: 6461383 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8321. Min Range: -2.8321
Max Act: 2.7844. Min Act: -0.1700
Data Index: 4267750 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8321. Min Range: -2.8321
Max Act: 2.7844. Min Act: -0.1700
Data Index: 8163659 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8321. Min Range: -2.8321
Max Act: 2.7844. Min Act: -0.1700
Data Index: 4083010 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8321. Min Range: -2.8321
Max Act: 2.7844. Min Act: -0.1700
Data Index: 5636578 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8321. Min Range: -2.8321
Max Act: 2.7684. Min Act: -0.1700
Data Index: 854581 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8321. Min Range: -2.8321
Max Act: 2.7684. Min Act: -0.1700
Data Index: 725831 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8321. Min Range: -2.8321
Max Act: 2.7844. Min Act: -0.1700
Data Index: 3079447 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8321. Min Range: -2.8321
Max Act: 2.7525. Min Act: -0.1700
Data Index: 4768520 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8321. Min Range: -2.8321
Max Act: 2.7525. Min Act: -0.1700
Data Index: 8540567 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8321. Min Range: -2.8321
Max Act: 2.7525. Min Act: -0.1700
Data Index: 6346854 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8321. Min Range: -2.8321
Max Act: 2.7365. Min Act: -0.1700
Data Index: 6299700 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8321. Min Range: -2.8321
Max Act: 2.7525. Min Act: -0.1700
Data Index: 4430781 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8321. Min Range: -2.8321
Max Act: 2.7365. Min Act: -0.1700
Data Index: 2145919 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8321. Min Range: -2.8321
Max Act: 2.7205. Min Act: -0.1700
Data Index: 5785387 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8321. Min Range: -2.8321
Max Act: 2.7365. Min Act: -0.1700
Data Index: 8424992 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8321. Min Range: -2.8321
Max Act: 2.7684. Min Act: -0.1700
Data Index: 7350446 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8321. Min Range: -2.8321
Max Act: 2.7365. Min Act: -0.1700
Data Index: 3663055 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #19