Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3537 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9696. Min Range: -5.9696
Max Act: 5.9696. Min Act: -0.1700
Data Index: 1672363 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9696. Min Range: -5.9696
Max Act: 5.8759. Min Act: -0.1700
Data Index: 5523403 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9696. Min Range: -5.9696
Max Act: 5.8446. Min Act: -0.1700
Data Index: 3493335 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9696. Min Range: -5.9696
Max Act: 5.8446. Min Act: -0.1700
Data Index: 2797592 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9696. Min Range: -5.9696
Max Act: 5.8134. Min Act: -0.1700
Data Index: 8010859 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9696. Min Range: -5.9696
Max Act: 5.8134. Min Act: -0.1700
Data Index: 3621082 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9696. Min Range: -5.9696
Max Act: 5.7821. Min Act: -0.1700
Data Index: 8596561 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9696. Min Range: -5.9696
Max Act: 5.7509. Min Act: -0.1700
Data Index: 804005 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9696. Min Range: -5.9696
Max Act: 5.7509. Min Act: -0.1700
Data Index: 8186511 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9696. Min Range: -5.9696
Max Act: 5.7196. Min Act: -0.1700
Data Index: 711028 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9696. Min Range: -5.9696
Max Act: 5.7196. Min Act: -0.1700
Data Index: 3684997 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9696. Min Range: -5.9696
Max Act: 5.7196. Min Act: -0.1700
Data Index: 2078917 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9696. Min Range: -5.9696
Max Act: 5.7196. Min Act: -0.1700
Data Index: 3684549 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9696. Min Range: -5.9696
Max Act: 5.7196. Min Act: -0.1700
Data Index: 3127771 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9696. Min Range: -5.9696
Max Act: 5.7196. Min Act: -0.1700
Data Index: 5485175 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9696. Min Range: -5.9696
Max Act: 5.7196. Min Act: -0.1700
Data Index: 4496049 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9696. Min Range: -5.9696
Max Act: 5.7196. Min Act: -0.1700
Data Index: 4027208 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9696. Min Range: -5.9696
Max Act: 5.7196. Min Act: -0.1700
Data Index: 7456690 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9696. Min Range: -5.9696
Max Act: 5.6884. Min Act: -0.1700
Data Index: 950589 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9696. Min Range: -5.9696
Max Act: 5.6884. Min Act: -0.1700
Data Index: 822737 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19