Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2876 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1264. Min Range: -5.1264
Max Act: 5.1264. Min Act: -0.1700
Data Index: 5249326 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1264. Min Range: -5.1264
Max Act: 5.0952. Min Act: -0.1700
Data Index: 2633392 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1264. Min Range: -5.1264
Max Act: 5.0014. Min Act: -0.1700
Data Index: 7528584 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1264. Min Range: -5.1264
Max Act: 4.9389. Min Act: -0.1700
Data Index: 222931 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1264. Min Range: -5.1264
Max Act: 4.9389. Min Act: -0.1700
Data Index: 7259687 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1264. Min Range: -5.1264
Max Act: 4.9077. Min Act: -0.1700
Data Index: 1449772 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1264. Min Range: -5.1264
Max Act: 4.8764. Min Act: -0.1700
Data Index: 7385483 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1264. Min Range: -5.1264
Max Act: 4.8764. Min Act: -0.1700
Data Index: 5025636 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1264. Min Range: -5.1264
Max Act: 4.8452. Min Act: -0.1700
Data Index: 1576170 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1264. Min Range: -5.1264
Max Act: 4.8452. Min Act: -0.1700
Data Index: 1006795 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1264. Min Range: -5.1264
Max Act: 4.8139. Min Act: -0.1700
Data Index: 3224052 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1264. Min Range: -5.1264
Max Act: 4.8139. Min Act: -0.1700
Data Index: 2759779 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1264. Min Range: -5.1264
Max Act: 4.7827. Min Act: -0.1700
Data Index: 6562620 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1264. Min Range: -5.1264
Max Act: 4.7202. Min Act: -0.1700
Data Index: 51641 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1264. Min Range: -5.1264
Max Act: 4.7202. Min Act: -0.1700
Data Index: 7647540 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1264. Min Range: -5.1264
Max Act: 4.7202. Min Act: -0.1700
Data Index: 4995250 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1264. Min Range: -5.1264
Max Act: 4.6889. Min Act: -0.1700
Data Index: 2253019 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1264. Min Range: -5.1264
Max Act: 4.6889. Min Act: -0.1700
Data Index: 3971444 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1264. Min Range: -5.1264
Max Act: 4.6577. Min Act: -0.1700
Data Index: 6802145 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1264. Min Range: -5.1264
Max Act: 4.6577. Min Act: -0.1700
Data Index: 1666988 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #19