Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 949 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6725. Min Range: -4.6725
Max Act: 4.6725. Min Act: -0.1700
Data Index: 8534371 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6725. Min Range: -4.6725
Max Act: 4.6100. Min Act: -0.1700
Data Index: 3635268 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6725. Min Range: -4.6725
Max Act: 4.6413. Min Act: -0.1700
Data Index: 570896 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6725. Min Range: -4.6725
Max Act: 4.5475. Min Act: -0.1700
Data Index: 1263565 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6725. Min Range: -4.6725
Max Act: 4.5788. Min Act: -0.1700
Data Index: 6919601 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6725. Min Range: -4.6725
Max Act: 4.5475. Min Act: -0.1700
Data Index: 6580137 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6725. Min Range: -4.6725
Max Act: 4.5163. Min Act: -0.1700
Data Index: 855602 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6725. Min Range: -4.6725
Max Act: 4.5163. Min Act: -0.1700
Data Index: 5547704 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6725. Min Range: -4.6725
Max Act: 4.5163. Min Act: -0.1700
Data Index: 1494478 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6725. Min Range: -4.6725
Max Act: 4.4850. Min Act: -0.1700
Data Index: 4395463 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6725. Min Range: -4.6725
Max Act: 4.4538. Min Act: -0.1700
Data Index: 5036366 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6725. Min Range: -4.6725
Max Act: 4.4538. Min Act: -0.1700
Data Index: 788523 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6725. Min Range: -4.6725
Max Act: 4.4538. Min Act: -0.1700
Data Index: 4817240 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6725. Min Range: -4.6725
Max Act: 4.4538. Min Act: -0.1700
Data Index: 3096929 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6725. Min Range: -4.6725
Max Act: 4.4538. Min Act: -0.1700
Data Index: 8202124 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6725. Min Range: -4.6725
Max Act: 4.4225. Min Act: -0.1700
Data Index: 8735506 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6725. Min Range: -4.6725
Max Act: 4.4225. Min Act: -0.1700
Data Index: 3589787 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6725. Min Range: -4.6725
Max Act: 4.4538. Min Act: -0.1700
Data Index: 1418578 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6725. Min Range: -4.6725
Max Act: 4.4225. Min Act: -0.1700
Data Index: 2695207 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6725. Min Range: -4.6725
Max Act: 4.4225. Min Act: -0.1700
Data Index: 5743428 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #19