Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3457 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4639. Min Range: -5.4639
Max Act: 5.4639. Min Act: -0.1700
Data Index: 4016666 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4639. Min Range: -5.4639
Max Act: 5.4014. Min Act: -0.1700
Data Index: 7813109 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4639. Min Range: -5.4639
Max Act: 5.2764. Min Act: -0.1700
Data Index: 6451580 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4639. Min Range: -5.4639
Max Act: 5.2139. Min Act: -0.1700
Data Index: 7970842 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4639. Min Range: -5.4639
Max Act: 5.1827. Min Act: -0.1700
Data Index: 195044 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4639. Min Range: -5.4639
Max Act: 5.1827. Min Act: -0.1700
Data Index: 6395594 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4639. Min Range: -5.4639
Max Act: 5.1514. Min Act: -0.1700
Data Index: 1257540 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4639. Min Range: -5.4639
Max Act: 5.1202. Min Act: -0.1700
Data Index: 5220975 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4639. Min Range: -5.4639
Max Act: 5.1514. Min Act: -0.1700
Data Index: 4426614 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4639. Min Range: -5.4639
Max Act: 5.1202. Min Act: -0.1700
Data Index: 2435 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4639. Min Range: -5.4639
Max Act: 5.0889. Min Act: -0.1700
Data Index: 1443887 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4639. Min Range: -5.4639
Max Act: 5.0889. Min Act: -0.1700
Data Index: 7001602 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4639. Min Range: -5.4639
Max Act: 5.0889. Min Act: -0.1700
Data Index: 5265435 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4639. Min Range: -5.4639
Max Act: 5.0889. Min Act: -0.1700
Data Index: 1864636 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4639. Min Range: -5.4639
Max Act: 5.0577. Min Act: -0.1700
Data Index: 2810218 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4639. Min Range: -5.4639
Max Act: 5.0264. Min Act: -0.1700
Data Index: 6038120 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4639. Min Range: -5.4639
Max Act: 5.0577. Min Act: -0.1700
Data Index: 7882929 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4639. Min Range: -5.4639
Max Act: 5.0577. Min Act: -0.1700
Data Index: 7896720 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4639. Min Range: -5.4639
Max Act: 5.0264. Min Act: -0.1700
Data Index: 5363191 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4639. Min Range: -5.4639
Max Act: 5.0264. Min Act: -0.1700
Data Index: 3626677 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19