Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2493 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2391. Min Range: -6.2391
Max Act: 6.2391. Min Act: -0.1700
Data Index: 6640741 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2391. Min Range: -6.2391
Max Act: 6.1141. Min Act: -0.1700
Data Index: 6899270 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2391. Min Range: -6.2391
Max Act: 6.0516. Min Act: -0.1700
Data Index: 5940279 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2391. Min Range: -6.2391
Max Act: 6.0203. Min Act: -0.1700
Data Index: 2435340 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2391. Min Range: -6.2391
Max Act: 6.0203. Min Act: -0.1700
Data Index: 7814168 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2391. Min Range: -6.2391
Max Act: 6.0516. Min Act: -0.1700
Data Index: 807472 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2391. Min Range: -6.2391
Max Act: 6.0516. Min Act: -0.1700
Data Index: 5776819 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2391. Min Range: -6.2391
Max Act: 6.0516. Min Act: -0.1700
Data Index: 5287340 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2391. Min Range: -6.2391
Max Act: 6.0203. Min Act: -0.1700
Data Index: 7371559 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2391. Min Range: -6.2391
Max Act: 5.9578. Min Act: -0.1700
Data Index: 7016850 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2391. Min Range: -6.2391
Max Act: 5.9891. Min Act: -0.1700
Data Index: 4850590 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2391. Min Range: -6.2391
Max Act: 5.9578. Min Act: -0.1700
Data Index: 5569783 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2391. Min Range: -6.2391
Max Act: 5.9891. Min Act: -0.1700
Data Index: 2175059 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2391. Min Range: -6.2391
Max Act: 5.9891. Min Act: -0.1700
Data Index: 3319948 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2391. Min Range: -6.2391
Max Act: 5.9891. Min Act: -0.1700
Data Index: 1912501 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2391. Min Range: -6.2391
Max Act: 5.9578. Min Act: -0.1700
Data Index: 6976266 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2391. Min Range: -6.2391
Max Act: 5.9578. Min Act: -0.1700
Data Index: 1944596 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2391. Min Range: -6.2391
Max Act: 5.9266. Min Act: -0.1700
Data Index: 8100921 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2391. Min Range: -6.2391
Max Act: 5.9266. Min Act: -0.1700
Data Index: 2947932 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2391. Min Range: -6.2391
Max Act: 5.9266. Min Act: -0.1700
Data Index: 6770609 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19