Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1870 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0639. Min Range: -6.0639
Max Act: 6.0639. Min Act: -0.1700
Data Index: 1071196 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0639. Min Range: -6.0639
Max Act: 5.8764. Min Act: -0.1700
Data Index: 4586156 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0639. Min Range: -6.0639
Max Act: 5.8139. Min Act: -0.1700
Data Index: 1935116 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0639. Min Range: -6.0639
Max Act: 5.6889. Min Act: -0.1700
Data Index: 3841609 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0639. Min Range: -6.0639
Max Act: 5.6576. Min Act: -0.1700
Data Index: 300789 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0639. Min Range: -6.0639
Max Act: 5.6576. Min Act: -0.1700
Data Index: 8095354 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0639. Min Range: -6.0639
Max Act: 5.6576. Min Act: -0.1700
Data Index: 759143 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0639. Min Range: -6.0639
Max Act: 5.6576. Min Act: -0.1700
Data Index: 851409 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0639. Min Range: -6.0639
Max Act: 5.5951. Min Act: -0.1700
Data Index: 4065013 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0639. Min Range: -6.0639
Max Act: 5.6264. Min Act: -0.1700
Data Index: 7113676 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0639. Min Range: -6.0639
Max Act: 5.6264. Min Act: -0.1700
Data Index: 4545992 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0639. Min Range: -6.0639
Max Act: 5.5951. Min Act: -0.1700
Data Index: 6540073 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0639. Min Range: -6.0639
Max Act: 5.5951. Min Act: -0.1700
Data Index: 3384458 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0639. Min Range: -6.0639
Max Act: 5.5951. Min Act: -0.1700
Data Index: 8216673 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0639. Min Range: -6.0639
Max Act: 5.5639. Min Act: -0.1700
Data Index: 7652684 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0639. Min Range: -6.0639
Max Act: 5.5639. Min Act: -0.1700
Data Index: 884866 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0639. Min Range: -6.0639
Max Act: 5.5639. Min Act: -0.1700
Data Index: 1189044 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0639. Min Range: -6.0639
Max Act: 5.5639. Min Act: -0.1700
Data Index: 2901701 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0639. Min Range: -6.0639
Max Act: 5.5326. Min Act: -0.1700
Data Index: 7626957 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0639. Min Range: -6.0639
Max Act: 5.5639. Min Act: -0.1700
Data Index: 5293295 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #19